id
stringlengths 10
13
| image
dict | conversations
listlengths 2
2
|
|---|---|---|
mind2web_2700 | {
"bytes": "",
"path": "./images/3be7acd4-c8c4-4e0d-b2b6-f82a4e17de8c_f321c6df-c46a-4b3c-85f6-255e8db91d65.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Open the Resident evil 4 game guide.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.071, 0.16, 0.079, 0.166] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2701 | {
"bytes": "",
"path": "./images/1b17b79c-589f-45eb-b55d-c977d1b9708e_8ae8c40d-2a52-496f-ac1b-a012fdf01d3f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest motel for 2 adults in Seattle from 11 May to 18 May\nPrevious actions:\n[option] Seattle (WA), United States (City) -> CLICK\n[button] Next Month -> CLICK\n[span] 11 -> CLICK\n[span] 18 -> CLICK\n[span] SEARCH -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.471, 0.289, 0.522, 0.306] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2702 | {
"bytes": "",
"path": "./images/b48c9974-4ba0-4112-98ce-3667781fa71b_513bf92e-6c28-43d9-9fb0-0d858631436c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a cheapest standard train ticket from London to Sheffield on March, 29, arriving by 10:45 am for 2 adults.\nPrevious actions:\n[listbox] minutes -> SELECT: 45\n[svg] -> CLICK\n[listbox] select adults -> SELECT: 2\n[button] Done -> CLICK\n[button] Get cheapest tickets -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.291, 0.393, 0.709, 0.418] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2703 | {
"bytes": "",
"path": "./images/0cb50efe-4568-4c8d-bf0e-ed106cf99d1d_dec7212a-0ef8-4cbe-86b6-1aa9f3ec293e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the all time most popular solo track by ArianaGrande\nPrevious actions:\n[link] Search -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.0, 0.0, 0.906, 0.037] in the image\nAnd my action is Action: TYPE\nValue: Ariana Grande"
}
]
|
mind2web_2704 | {
"bytes": "",
"path": "./images/e6bdb364-4327-44f0-a6d8-94eb00b36ca7_51845b7f-fb7b-4bc3-9c13-2c0a2afb5e26.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Go to the page with help in choosing a solar energy product for homes.\nPrevious actions:\n[link] Solar Panels -> CLICK\n[link] Order Now -> CLICK\n[button] Help Me Choose Solar -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.713, 0.448, 0.838, 0.485] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2705 | {
"bytes": "",
"path": "./images/e344b89e-767a-4618-ba82-4b81cdcba280_0aa34099-a83e-4931-897f-1f1b7e0f7e16.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: add a motherboard under $200 and a compatible processor at any price to the shopping cart.\nPrevious actions:\n[searchbox] Search Site -> TYPE: motherboard\n[button] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.125, 0.507, 0.192, 0.524] in the image\nAnd my action is Action: TYPE\nValue: 200"
}
]
|
mind2web_2706 | {
"bytes": "",
"path": "./images/e62d1f6c-d98c-4ea2-b699-527eeedf3e9b_91afaca3-3df5-479e-aa43-1717da3b664c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Order an adult’s bottomless bubbles package for Joe Bloggs who is booked onto cruise 101010\nPrevious actions:\n[img] -> CLICK\n[link] Beverage Packages -> CLICK\n[button] add Bottomless Bubbles to the cart with price $9.5... -> CLICK\n[div] I want to give a gift to a booked cruiser -> CLICK\n[textbox] first-name -> TYPE: Joe"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.122, 0.312, 0.352, 0.33] in the image\nAnd my action is Action: TYPE\nValue: Bloggs"
}
]
|
mind2web_2707 | {
"bytes": "",
"path": "./images/b467797c-5fab-4ee6-9b1f-ac6dc50c05cf_4ddee31b-ec7d-496c-a1bb-92e16c3306ef.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest-priced single pack of Xerox genuine magenta toner sold by Newegg with free shipping.\nPrevious actions:\n[link] Computer Peripherals -> CLICK\n[link] Printer Ink & Toner -> CLICK\n[link] Xerox Toner -> CLICK\n[span] Newegg -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.148, 0.371, 0.192, 0.385] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2708 | {
"bytes": "",
"path": "./images/ca049641-9721-4593-95c5-a47e22365b5b_e8eeebb3-8539-4adf-830b-b6bfeaa8a609.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest new electric car with highest ev mile range per charge, see the details of the top result.\nPrevious actions:\n[link] Cars for Sale -> HOVER\n[link] Cars for Sale -> CLICK\n[checkbox] New (9,776) -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.113, 0.608, 0.296, 0.631] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2709 | {
"bytes": "",
"path": "./images/6ab8130f-362c-4fc3-bdab-d0528f0c6181_41d4cbcd-ea80-4132-a2c9-b4da47c6a95f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[button] Search -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.081, 0.416, 0.263, 0.426] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2710 | {
"bytes": "",
"path": "./images/d0ac6860-23f7-40c1-b30d-12269470d2c3_afa1433c-8d13-4e0d-9b05-e0d7299da884.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check prices of organic strawberries with three different stores and add the one with lowest price to cart for 94105.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.225, 0.011, 0.776, 0.063] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2711 | {
"bytes": "",
"path": "./images/bf469f30-6628-4017-b963-672645d7feab_51e9982e-0a95-4525-af85-fba89b577a34.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the highest rated dog collar under 10 dollar.\nPrevious actions:\n[span] Category -> CLICK\n[link] Collars & Leashes (485) -> CLICK\n[link] Sort by: Featured -> CLICK\n[link] Highest Rated -> CLICK\n[div] Price -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.016, 0.477, 0.098, 0.491] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2712 | {
"bytes": "",
"path": "./images/4786982f-25f5-4bf8-bb91-522656489f63_776e07ac-4fec-47f9-8642-b4aa8dfe359e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Reserve the cheapest hotel with 5 stars and free wifi located in downtown dc in Washington on June 5 for 4 adults in 2 rooms.\nPrevious actions:\n[svg] -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK\n[button] Done -> CLICK\n[svg] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.081, 0.6, 0.263, 0.609] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2713 | {
"bytes": "",
"path": "./images/1a038b20-cd5a-4c32-8b11-fe2aeeb4ec85_4b8526ca-6237-4769-b1de-06e1097f8783.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: View Fares from Grand Central to Stoney Brook for Port Jefferson after 10:00pm for adult.\nPrevious actions:\n[link] Fares & Tolls -> CLICK\n[link] See railroad fare details. -> CLICK\n[link] Plan a trip to see fares. -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.145, 0.317, 0.474, 0.347] in the image\nAnd my action is Action: TYPE\nValue: grand central"
}
]
|
mind2web_2714 | {
"bytes": "",
"path": "./images/6ab8130f-362c-4fc3-bdab-d0528f0c6181_f0038f74-a616-44cf-b13a-29111280ae8b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest 3-star hotel or resort for two within a budget of 50 to 100 dollars for four days starting from April 25, near the beach in goa that offers breakfast, wifi, a swimming pool, and free cancellation.\nPrevious actions:\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.294, 0.246, 0.436, 0.263] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2715 | {
"bytes": "",
"path": "./images/10e17667-f9cf-4a68-adcd-ad2677c3f385_4077127f-bf53-43c9-8fff-96ffb9ecb611.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find series 1 and series 2 BMW vehicles in the store nearest to 07055\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.031, 0.323, 0.237, 0.361] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2716 | {
"bytes": "",
"path": "./images/9ea9ac0d-8c31-49bc-aa3d-e85b80580409_bdf6ba83-c40c-4f99-89e1-56131fab37b1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the flight schedule between London and New York for April 7 and check the upgrade details of the noon flight.\nPrevious actions:\n[heading] Flight status -> CLICK\n[combobox] Enter your departing city, airport name, or airpor... -> TYPE: london\n[span] London -> CLICK\n[combobox] Enter your destination city, airport name, or airp... -> TYPE: new york"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.299, 0.176, 0.539, 0.183] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2717 | {
"bytes": "",
"path": "./images/38fe67f7-14af-4259-8309-aa350abdc395_9c7a03fc-35cc-4769-869b-469e1363dca2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for the cheapest two rooms near Kashi Vishwanath Temple in India for three adults and a 7-year-old kid from June 6 to 10 in any 3-star and up air-conditioned family hotel with a review score of at least 8, free internet.\nPrevious actions:\n[link] Search for hotels -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.241, 0.09, 0.478, 0.112] in the image\nAnd my action is Action: TYPE\nValue: kashi vishwanath temple"
}
]
|
mind2web_2718 | {
"bytes": "",
"path": "./images/7c28f4e3-3dcf-477b-98c3-087c4fc16655_55ba9bda-3735-48f8-8ce5-bdb904725fe2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate a store which is nearest to 10017 zip code.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.122, 0.739, 0.2, 0.753] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2719 | {
"bytes": "",
"path": "./images/7c2ab1ed-54b7-4316-8b2f-d7467e01b540_a77a3a7f-cc1d-447b-903a-d09588b8a89c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get the cheapest direct flight from Madurai to Chennai on 20/3/23 booking through Air India.com\nPrevious actions:\n[link] Search for flights -> CLICK\n[textbox] Flight origin input -> TYPE: madurai\n[div] Madurai, Tamil Nadu, India -> CLICK\n[path] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.931, 0.131, 0.975, 0.164] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2720 | {
"bytes": "",
"path": "./images/bb02400d-e9da-416a-839a-0068f511a630_4bb48e3e-2a32-4135-b436-33621055fc36.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get WWE tickets for April 10 event happening in seattle, and book 4 cheapest lower level tickets.\nPrevious actions:\n[link] WWE Tickets -> CLICK\n[link] TICKETS -> CLICK\n[p] Any Quantity -> CLICK\n[label] 4 -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.48, 0.333, 0.652, 0.366] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2721 | {
"bytes": "",
"path": "./images/5f09e15c-c987-4bdb-ab6e-5db39b18317d_1f4c17d0-a075-4249-8621-8b8366006cca.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book 3 tickets for a Special Event or Experience in Miami on may 4\nPrevious actions:\n[svg] -> CLICK\n[button] Miami -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.145, 0.018, 0.418, 0.04] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2722 | {
"bytes": "",
"path": "./images/75db63ac-4fcf-400e-833f-d31f00cf6ab6_dff98ff2-9f90-4274-abe1-de38cb0767d3.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find nearby top-rated restaurants in Chicago, save the restaurant, and then book a table for 7 people on April 20 for lunch at 2 pm.\nPrevious actions:\n[button] Today -> CLICK\n[button] April 20, 2023. -> CLICK\n[combobox] Party of 2 -> SELECT: 7 Guests\n[svg] -> CLICK\n[button] View more availability for Canal Street Eatery & M... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.023, 0.212, 0.185, 0.233] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2723 | {
"bytes": "",
"path": "./images/d1de3d1a-3df1-4421-98f3-f8d078752893_d683e390-ec8a-47db-8772-cb52166ae30d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest cab with GPS and unlimited e-toll, and pay now for an option for a military veteran with pick up from the nearest location to Nevada City, California, on June 6, 11 am, and drop off at the exact location on June 10, 1 pm.\nPrevious actions:\n[link] 10 -> CLICK\n[combobox] Return Time -> SELECT: 1:00 PM\n[button] Select My Car -> CLICK\n[link] Pay Now -> CLICK\n[checkbox] $14.45/Day$13.95/Day -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.746, 0.621, 0.777, 0.657] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2724 | {
"bytes": "",
"path": "./images/c2e4800e-684f-4bb6-99ab-782806c8776d_a2e11919-3d09-4a0d-bcb1-521927016889.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for McDonalds located in Greenvill, SC.\nPrevious actions:\n[textbox] Near -> CLICK\n[textbox] Near -> TYPE: Greenville\n[span] Greenville -> CLICK\n[textbox] Find -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.131, 0.022, 0.335, 0.036] in the image\nAnd my action is Action: TYPE\nValue: McDonalds"
}
]
|
mind2web_2725 | {
"bytes": "",
"path": "./images/a52774d2-550d-475a-922c-25c37d44557c_59920c95-802a-4e3d-b08b-4807653406d4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: I want to see mansions for 3 adults to stay in in europe during any month\nPrevious actions:\n[button] Check in / Check out Any week -> CLICK\n[tab] Flexible dates -> CLICK\n[label] Month -> CLICK\n[div] Add guests -> CLICK\n[path] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.768, 0.108, 0.793, 0.121] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2726 | {
"bytes": "",
"path": "./images/0f63c624-6097-473e-ad19-59bc139836d1_ea3e7300-7769-45d1-b36e-1958830a8e3e.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for developer jobs in Dallas, Texas, and review details of the latest job then create an 8-day alert after signing in.\nPrevious actions:\n[link] View All Jobs -> CLICK\n[textbox] Search by Keyword -> TYPE: developer\n[textbox] Search by Location -> TYPE: dallas\n[button] Search Jobs -> CLICK\n[link] Developer/ Senior Developer, IT -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.309, 0.249, 0.349, 0.277] in the image\nAnd my action is Action: TYPE\nValue: 8"
}
]
|
mind2web_2727 | {
"bytes": "",
"path": "./images/74b456b6-0e62-429f-b13c-45861f2cdf82_e99bb9c7-aeec-4826-b8f8-407c00622c61.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a recent full-time job in United Airlines corporate in Gurugram, India if a job in sales is available, then apply through email at [email protected].\nPrevious actions:\n[span] -> CLICK\n[button] State / Province -> CLICK\n[span] -> CLICK\n[button] City -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.027, 0.227, 0.245, 0.261] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2728 | {
"bytes": "",
"path": "./images/6e98e331-c80b-4316-b332-af76c4cb2440_4abed667-f469-420b-9820-825cdd9e9b91.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for women's golf polos in m size, priced between 50 to 75 dollars, and save the lowest priced among results.\nPrevious actions:\n[menuitem] Women -> HOVER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.603, 0.133, 0.623, 0.149] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2729 | {
"bytes": "",
"path": "./images/87ca0d6a-c513-4aae-b14f-7d4db3255e98_e834b996-182e-4755-bc68-504eb48496ca.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a flight from Dublin in Ireland to Paris Beauvais in france for 2 adults leaving apr 26 and returning may 2 with the promo code 10000001\nPrevious actions:\n[textbox] From -> CLICK\n[button] Ireland -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.523, 0.22, 0.715, 0.238] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2730 | {
"bytes": "",
"path": "./images/85706225-aa42-43c1-8cfa-8696118698a2_3f0533c7-e459-49b9-801c-2da4e0a3b04d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the status of flights from Los Angeles area to Boston area tomorrow\nPrevious actions:\n[option] Los Angeles area -> CLICK\n[textbox] To -> TYPE: Boston\n[option] Boston area -> CLICK\n[button] Today, Tue Apr 11 -> CLICK\n[span] Tomorrow, Wed Apr 12 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.422, 0.272, 0.578, 0.318] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2731 | {
"bytes": "",
"path": "./images/40cd58cd-6c9a-47b9-a927-92243970d87a_d53a6991-303f-429e-a864-ef07350fe423.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find monthly daytime only parking nearest to Madison Square Garden starting from April 22\nPrevious actions:\n[tab] Monthly -> CLICK\n[textbox] Search for parking -> TYPE: madison square garden\n[li] Madison Square Garden, Pennsylvania Plaza, New Yor... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.016, 0.316, 0.161, 0.345] in the image\nAnd my action is Action: SELECT\nValue: Daytime Only Parking"
}
]
|
mind2web_2732 | {
"bytes": "",
"path": "./images/839ad551-da04-4c8e-96c3-093e762ea167_b76c6f62-43c7-465e-98ff-39332220d881.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search and book the cheapest daytime only monthly parking option in Seattle near Stripe, 5th Avenue\nPrevious actions:\n[textbox] Search for parking -> TYPE: stripe, 5th avenue\n[li] Stripe, 5th Avenue, Seattle, WA, USA -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.058, 0.069, 0.094, 0.094] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2733 | {
"bytes": "",
"path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_f23cef2f-fa8c-4eb9-b7a4-4ece33aacea0.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[div] 1 Small Bag only -> CLICK\n[label] -> CLICK\n[button] Continue -> CLICK\n[button] No thanks -> CLICK\n[button] Continue -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.841, 0.702, 0.953, 0.749] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2734 | {
"bytes": "",
"path": "./images/3bb1c925-71ef-4713-a139-a3be65f8a7a5_39fe4719-f218-4d71-aab6-f8e6a4082dad.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show reviews for Fallout 4 and mark the first one as helpful.\nPrevious actions:\n[textbox] search -> TYPE: Fallout 4"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.626, 0.097, 0.949, 0.127] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2735 | {
"bytes": "",
"path": "./images/8865ca64-0df2-4e3f-905d-a9e07e1eeb68_4f88ffbf-3206-47b4-84d2-d849707ed499.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show bike service charges for store at Lafayette St, 10013.\nPrevious actions:\n[button] Cycle -> CLICK\n[link] Shop Services -> CLICK\n[link] Find a bike shop near you -> CLICK\n[textbox] Enter ZIP or City, State -> TYPE: 10013"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.347, 0.818, 0.366, 0.831] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2736 | {
"bytes": "",
"path": "./images/0b16b42c-dea7-4079-a2a8-79eb23447193_ee1e8ed0-43c7-4576-941e-61bb00b10218.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find popular deals to USA national parks in the southeast region of Biscayne national park, and add to the cart the fully refundable economy flight from New York to Miami with a departure date of May 13 and a return date of May 18.\nPrevious actions:\n[textbox] Departure -> CLICK\n[gridcell] Saturday, May 13, 2023 -> CLICK\n[gridcell] Thursday, May 18, 2023 -> CLICK\n[button] Search flights -> CLICK\n[span] Refundable fares -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.443, 0.191, 0.458, 0.202] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2737 | {
"bytes": "",
"path": "./images/2ce0a80e-a049-434d-8b99-8343d2a0b21d_eea67014-a3f9-41e0-8b0e-e2ca7dd69079.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me the location of the Altavista bus stop.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.356, 0.0, 0.44, 0.047] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2738 | {
"bytes": "",
"path": "./images/ca80bb42-2617-4f29-bbcd-bcc426b3e407_adb3f628-dbad-4824-8d8b-c53ac8161b15.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Airport information of Camarillo Airport, CA and check weather.\nPrevious actions:\n[combobox] Search Method -> SELECT: Airport"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.454, 0.031, 0.602, 0.049] in the image\nAnd my action is Action: TYPE\nValue: Camarillo"
}
]
|
mind2web_2739 | {
"bytes": "",
"path": "./images/44dcda68-082c-455a-a409-7091470cc006_888c5867-268f-4edc-a635-9bc336f1fef5.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets from Edinburgh Waverly to Glagsgow Central on May 18, leaving nearest 3PM for 1 adult with a Veterans Railcard\nPrevious actions:\n[combobox] Departure station, none selected. Select a station... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.113, 0.049, 0.327, 0.064] in the image\nAnd my action is Action: TYPE\nValue: Edinburgh"
}
]
|
mind2web_2740 | {
"bytes": "",
"path": "./images/4097c577-e637-4543-87a3-09b2f4734163_0e2f5a42-2c2b-4554-9ec1-5e5a78e2f12c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a pedicure salon in New York and add two to favorites.\nPrevious actions:\n[input] -> TYPE: pedicure salon\n[input] -> TYPE: New York\n[link] New York, NY -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.586, 0.163, 0.664, 0.196] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2741 | {
"bytes": "",
"path": "./images/4097c577-e637-4543-87a3-09b2f4734163_48956859-b850-47a4-a0a2-7c0bdc12231f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a pedicure salon in New York and add two to favorites.\nPrevious actions:\n[input] -> TYPE: pedicure salon\n[input] -> TYPE: New York\n[link] New York, NY -> CLICK\n[button] Find -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.213, 0.342, 0.394, 0.35] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2742 | {
"bytes": "",
"path": "./images/92ba0696-bc54-41c9-8ddf-1a2f44420c6f_c72c3d18-5a88-42c8-8c16-9294a6019000.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Plan an accessible trip from empire state building to little Caribbean with least walking\nPrevious actions:\n[searchbox] From -> CLICK\n[searchbox] From -> TYPE: empire state building"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.141, 0.274, 0.359, 0.315] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2743 | {
"bytes": "",
"path": "./images/b49f0d3e-7047-41df-9b4f-c2c15b1d3f70_3f010014-c3fd-457c-a17d-1ab30ce9a333.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find The Ritz-Carlton hotels in Washington DC that can hold a student social event from May 9 to May 12 and will require 7 guest rooms and an event space for 50\nPrevious actions:\n[textbox] Start Date -> CLICK\n[button] -> CLICK\n[gridcell] Tue, May 9, 2023 -> CLICK\n[gridcell] Fri, May 12, 2023 -> CLICK\n[div] Purpose of your event -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.664, 0.251, 0.958, 0.285] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2744 | {
"bytes": "",
"path": "./images/4ff347e6-e911-4af5-8151-7805a9e91b28_7ac03130-a5e7-41b0-a3bc-01c1cb99f1da.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show current alerts for red line subway.\nPrevious actions:\n[tab] Alerts -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.377, 0.166, 0.392, 0.177] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2745 | {
"bytes": "",
"path": "./images/bd32af6e-9fae-4968-b3e6-d143f148f5b8_e0931dce-0e84-42f5-91eb-b97b8d727e00.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy a copy of the Gorillaz first studio album.\nPrevious actions:\n[combobox] Search artists, albums and more... -> TYPE: gorillaz"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.141, 0.113, 0.489, 0.156] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2746 | {
"bytes": "",
"path": "./images/987b25a8-05af-4b18-bd5b-7e2ccba5fb1e_4c77cf02-5428-4f24-86c3-dd73dee21f63.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Add Western Digital internal SSD with 1TB storage and 8GB Ram DDR to the cart.\nPrevious actions:\n[link] Western Digital WD_BLACK SN770 M.2 2280 1TB PCIe G... -> CLICK\n[button] ADD TO CART -> CLICK\n[button] NO, THANKS -> CLICK\n[button] Close -> CLICK\n[searchbox] Search Site -> TYPE: 8GB Ram"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.496, 0.01, 0.546, 0.031] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2747 | {
"bytes": "",
"path": "./images/c1a354a1-7990-4ca8-9fc5-2fdb1b5df337_ee0ac3c1-985e-43a9-915e-f489f926b0a5.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a book in Hindi with ISBN 1648926800.\nPrevious actions:\n[link] Advanced Search -> CLICK\n[input] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.349, 0.342, 0.651, 0.374] in the image\nAnd my action is Action: TYPE\nValue: 1648926800"
}
]
|
mind2web_2748 | {
"bytes": "",
"path": "./images/8e7b05d4-7dfb-4345-af2b-3e1dcd1c2ea2_7232efcc-03a5-4cf6-abca-52d962651164.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me a map with charging stations in London.\nPrevious actions:\n[button] Menu -> CLICK\n[link] Charging -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.037, 0.186, 0.294, 0.22] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2749 | {
"bytes": "",
"path": "./images/10593972-6b1d-4b07-ba61-cb56ca0f06e3_ddadf800-5a52-419b-a717-ac5acbec55d1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a Lenovo laptop under $800 and create a price alert for $400.\nPrevious actions:\n[searchbox] Search Site -> TYPE: lenovo laptop\n[button] -> CLICK\n[div] Newest Lenovo Ideapad 3i Laptop, 14\" FHD Display, ... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.87, 0.268, 0.952, 0.281] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2750 | {
"bytes": "",
"path": "./images/1655f54a-31e5-4dda-9089-7ccff35a1095_7baddb2c-fc8d-44cf-be47-7d265a0c1d8c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the trip ideas for US travels and book small size or full-size pacific coast highway road trip for a Vietnamese from Los Angeles International Airport on July 7, 1 pm pick up and drop off at the same location on July 15, 2 pm.\nPrevious actions:\n[link] Trip Ideas -> CLICK\n[div] Pacific Coast Highway Road Trip -> CLICK\n[textbox] Enter your pick-up location or zip code -> TYPE: LOS ANGELES\n[span] Los Angeles Intl Airport -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.504, 0.071, 0.697, 0.092] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2751 | {
"bytes": "",
"path": "./images/1bd729e8-abb2-4649-bb81-8c790c04f8ad_450227c9-df44-4ea7-a169-6997823c8105.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a multi-purpose painting tool available for pick up at zip 44240, if the brand Red Devil is available, add the cheapest one to the wishlist and view my complete wish list.\nPrevious actions:\n[button] Departments -> CLICK\n[button] Paint -> CLICK\n[link] Painting Tools -> CLICK\n[button] 43229 -> TYPE: 44240\n[button] UPDATE -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.028, 0.272, 0.153, 0.286] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2752 | {
"bytes": "",
"path": "./images/446e3135-8a53-455f-9471-9f6660f6a94d_9137881e-849f-4da9-bf17-076132e3b61d.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a best business class flight ticket from Colombo to New York with a two-day Qatar stopover for 2 adults and 1 child on June 24.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.06, 0.294, 0.28, 0.324] in the image\nAnd my action is Action: TYPE\nValue: colombo"
}
]
|
mind2web_2753 | {
"bytes": "",
"path": "./images/e832e1f9-3a9d-440e-a96f-8cbbf241e4af_44d4df9f-e984-403f-aefb-96169d606b23.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Sell my single-key black car, which has no defect with a leather interior through Louisiana, license plate number YAW639 in zip 70726 with mileage of 222900, get the offer at my email [email protected].\nPrevious actions:\n[button] Next -> CLICK\n[textbox] Mileage -> TYPE: 222900\n[button] Next -> CLICK\n[span] -> CLICK\n[div] Leather -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.037, 0.309, 0.096, 0.346] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2754 | {
"bytes": "",
"path": "./images/d6dd19a2-c57e-4e4d-b7e1-8919a86f1157_ecd96a58-af68-400d-bac5-e637de08d916.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book the cheapest likely to sell out activity in Los Angeles on April 2\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.271, 0.296, 0.463, 0.306] in the image\nAnd my action is Action: TYPE\nValue: Los Angeles"
}
]
|
mind2web_2755 | {
"bytes": "",
"path": "./images/8b4e49e9-9802-4c1f-acb3-de06e38445e7_18636549-3ec4-44ab-9778-216113946411.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find beauty salons that are rated A and accept coupons in Seattle, WA.\nPrevious actions:\n[input] -> TYPE: beauty salons\n[link] Beauty Salons -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.493, 0.007, 0.789, 0.03] in the image\nAnd my action is Action: TYPE\nValue: Seattle, WA"
}
]
|
mind2web_2756 | {
"bytes": "",
"path": "./images/d3a4e6c3-65e8-46f7-8dd7-439bc559af2a_0310c46b-bca5-4bd5-b568-7af5cce54b97.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find value of 2016 Toyota Camry XLE Sedan 4D in black color with number plate AZXA46.\nPrevious actions:\n[generic] Black image Black -> CLICK\n[button] Next -> CLICK\n[span] -> CLICK\n[button] Next -> CLICK\n[div] License Plate -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.386, 0.223, 0.473, 0.236] in the image\nAnd my action is Action: TYPE\nValue: AZXA46"
}
]
|
mind2web_2757 | {
"bytes": "",
"path": "./images/1203a016-d541-4914-9cdb-f042ad0abcf5_3bc7e106-2d01-485b-bf0d-a1f32cca0604.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse Anime TV shows and sorty by Newest\nPrevious actions:\n[link] TV SHOWS -> CLICK\n[svg] -> CLICK\n[div] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.396, 0.624, 0.52, 0.659] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2758 | {
"bytes": "",
"path": "./images/b910229f-6133-452c-a640-6a6ec67b668b_7911af81-53d1-402e-acf4-53625f86f726.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Get quote for Amtrak vacation for two adults across country while leaving from Chicago on the 22nd of April. It should include Deluxe bedroom. The passenger is named John Mark with email address of [email protected] and phone number of 234567890.\nPrevious actions:\n[textbox] About Your Trip: -> TYPE: Wedding Anniversary\n[button] Continue -> CLICK\n[textbox] *First Name -> TYPE: John\n[textbox] *Last Name -> TYPE: Mark\n[textbox] *Email Address -> TYPE: [email protected]"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.289, 0.35, 0.711, 0.383] in the image\nAnd my action is Action: TYPE\nValue: 234567890"
}
]
|
mind2web_2759 | {
"bytes": "",
"path": "./images/270c18c6-b3cf-4409-ba6b-18160525692f_26a9327f-ce5d-41b5-b34f-e87ee369fe33.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest used and working Nintendo Switch for under $400 that can be bought right now.\nPrevious actions:\n[combobox] Search for anything -> TYPE: Nintendo Switch Console"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.786, 0.044, 0.917, 0.084] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2760 | {
"bytes": "",
"path": "./images/2b29b7d1-bd80-4d2c-a491-9dfc89827e84_163ac6b4-cfa8-4e29-8a90-0e0b9ed3c8c1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse best selling black hoodies in mens size Big and Tall that is between $25 and $50.\nPrevious actions:\n[div] Size Range -> CLICK\n[link] Big & Tall (5,552) -> CLICK\n[div] Price -> CLICK\n[link] $25 to $50 (2,237) -> CLICK\n[link] Sort by: Featured -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.808, 0.392, 0.974, 0.426] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2761 | {
"bytes": "",
"path": "./images/e62bcf45-0be3-4195-b234-37755d6d715e_d4753161-a0e6-48a8-bd37-6dacdc712fa9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a book by Sam Harris that has a rating of at least 4 stars and is available in paperback format.\nPrevious actions:\n[textbox] Search Amazon -> TYPE: Sam Harris\n[button] sam harris -> CLICK\n[region] 4 Stars & Up -> CLICK\n[link] Paperback -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.242, 0.413, 0.428, 0.447] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2762 | {
"bytes": "",
"path": "./images/3b390b60-5c04-40ee-a5af-353def43ffbc_8ee0dcc3-5cfd-49ec-9324-4e578df23877.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show me japanese restaurants in Fresno with online delivery.\nPrevious actions:\n[link] CITY PAGES -> CLICK\n[link] Fresno -> CLICK\n[img] -> CLICK\n[span] Order Online -> CLICK\n[link] All -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.423, 0.237, 0.575, 0.247] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2763 | {
"bytes": "",
"path": "./images/930803d7-4032-4144-89a2-e44f3c5c9ccf_bd9a4601-4e54-41e7-ba10-2c10b0d6f156.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Buy tickets for a group at Hurricane harbor Phoenix on April 22\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.515, 0.621, 0.783, 0.683] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2764 | {
"bytes": "",
"path": "./images/f7c2c65f-9415-4e1e-8ce7-a2e22ff2492c_dd9f6105-c072-46c9-b958-1a67631c68b9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the quickest one-way flight from New York To Paris on June 4 for two adults with one carry-on and one check-in bag in business class.\nPrevious actions:\n[svg] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.211, 0.072, 0.292, 0.088] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2765 | {
"bytes": "",
"path": "./images/56e4a9c1-d39e-4173-9857-9cf980c0fba9_05b31466-ca97-48e8-a8b5-d7be869d2c7f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Follow the Denver Nuggets NBA team.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.311, 0.063, 0.335, 0.072] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2766 | {
"bytes": "",
"path": "./images/14d4edf5-e5ca-40e8-8e5d-77068a22c32c_33c7a999-38ef-4589-8279-fdf8c2302c63.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: check the scores of the premiership on 19th of March.\nPrevious actions:\n[heading] SOCCER -> CLICK\n[a] FEATURED MATCHES -> CLICK\n[link] ENGLISH PREMIER LEAGUE -> CLICK\n[div] -> CLICK\n[div] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.43, 0.309, 0.454, 0.333] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2767 | {
"bytes": "",
"path": "./images/6e98e331-c80b-4316-b332-af76c4cb2440_c5d08604-1632-41cd-89c7-39dbdcb8a353.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for women's golf polos in m size, priced between 50 to 75 dollars, and save the lowest priced among results.\nPrevious actions:\n[link] Polos -> CLICK\n[div] Size -> CLICK\n[link] M -> CLICK\n[span] Now Trending -> CLICK\n[li] Price (Low - High) -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.464, 0.261, 0.485, 0.288] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2768 | {
"bytes": "",
"path": "./images/1ee63f83-8b6a-4883-813f-63f589e6e52b_b315afc2-75f7-4067-a09b-2a8b3b31c8b4.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book two rooms in the cheapest 3-star hotel which provides free breakfast, and free airport transportation for three adults, and one child from April 22 to 25 in texas city, the hotel should provide amenities for kids.\nPrevious actions:\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[span] -> CLICK\n[div] Recommended -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.842, 0.249, 0.96, 0.272] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2769 | {
"bytes": "",
"path": "./images/e9a5ab90-517c-4323-a343-6e10e6b9632f_efa0a116-02af-4a54-a426-72d5b7f09ac1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the gift registry of Carla Cahill, when asked for password use Michael Cahill as name and [email protected] as email.\nPrevious actions:\n[link] Gift Registry -> CLICK\n[span] Find a Registry -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.235, 0.16, 0.376, 0.177] in the image\nAnd my action is Action: TYPE\nValue: Carla"
}
]
|
mind2web_2770 | {
"bytes": "",
"path": "./images/e62bcf45-0be3-4195-b234-37755d6d715e_f1fcb650-e85a-459c-a24f-1140130da6b5.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a book by Sam Harris that has a rating of at least 4 stars and is available in paperback format.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.28, 0.004, 0.651, 0.02] in the image\nAnd my action is Action: TYPE\nValue: Sam Harris"
}
]
|
mind2web_2771 | {
"bytes": "",
"path": "./images/d0ce3db1-720b-4333-a487-2bdc8fd74a80_302070c4-a7ae-4fc4-957d-f31444de6ed6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Show episodes of Alien Worlds and check where to watch Episode 4 of Season 1.\nPrevious actions:\n[textbox] Search TV Shows and Movies... -> TYPE: Alien Worlds"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.062, 0.151, 0.594, 0.159] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2772 | {
"bytes": "",
"path": "./images/0f9dd411-f3ab-494e-8a3a-5dc9a908f4ee_2046ff41-f18c-401b-b0b6-acb8c47d4752.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Locate the cvs pharmacy nearest to zip code 45201 that provides hair loss evaluation and treatment.\nPrevious actions:\n[p] Skin, Hair & Nails -> CLICK\n[span] In-Person Care -> CLICK\n[button] Hair Loss Evaluation & Treatment -> CLICK\n[link] Hair Loss Evaluation & Treatment -> CLICK\n[textbox] Tell us a location Enter a ZIP code or city & stat... -> TYPE: 45201"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.352, 0.22, 0.514, 0.238] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2773 | {
"bytes": "",
"path": "./images/7180c4d1-971b-418d-8a64-87ab0d29c20e_a78fc3b8-5fae-4252-baf5-97f41c62fb6b.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the lowest rent truck for 4 people, pick up from JFK airport at 11 am on March 27 and return at noon on March 30.\nPrevious actions:\n[span] New York -> CLICK\n[button] Selected Pick-Up Date 03/22/2023 -> CLICK\n[button] 03/27/2023 -> CLICK\n[combobox] Pick-Up Time Selector -> SELECT: 11:00 AM\n[button] Date -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.354, 0.271, 0.393, 0.291] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2774 | {
"bytes": "",
"path": "./images/3358dffd-3673-435b-bfcb-cb242a2c622c_1745b057-153d-4830-9fc0-a0dd6789d5bb.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse round-trip bus tickets from Houston to Dallas leaving on May 7th and returning a week later.\nPrevious actions:\n[textbox] To (type text or use the arrow keys) -> TYPE: Dallas\n[div] Dallas, TX -> CLICK\n[input] -> CLICK\n[button] Next month -> CLICK\n[gridcell] May 07, 2023 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.763, 0.2, 0.903, 0.217] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2775 | {
"bytes": "",
"path": "./images/e3486ac5-6d1e-476f-b389-2e6df37f94bd_dd90c01f-05ab-4d6e-bfa5-3e9a3c00d161.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search a cheapest homestay with balcony in Bali, Indoneshia from April 1 to 4 for 2 adults and 4 children aged 3, 5, 8, and 12 years, respectively, double beds prefered, including breakfast.\nPrevious actions:\n[combobox] Age of Child 4(Child's age (years)) -> SELECT: 12\n[span] SEARCH -> CLICK\n[span] SEARCH -> CLICK\n[checkbox] list-filter-item-label-4 -> CLICK\n[checkbox] list-filter-item-label-12 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.077, 0.67, 0.089, 0.677] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2776 | {
"bytes": "",
"path": "./images/4b33554f-eb29-4f8d-93cf-5e947e4f8e47_adf176ec-c852-40c8-842f-2c4133f8aa43.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for restaurants near my location with pizza and for 6 customers.\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: Pizza"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.201, 0.101, 0.244, 0.125] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2777 | {
"bytes": "",
"path": "./images/1ced6d51-577b-4e85-b96e-b823dbbcbf29_6544d313-8e7a-42e9-a996-497789511924.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a newly listed pre-owned man Nike shoe in size 9 with free local pickup under 75 dollars.\nPrevious actions:\n[link] Fashion -> HOVER\n[link] Men's Shoes -> CLICK\n[link] Nike -> CLICK\n[button] US Shoe Size -> CLICK\n[link] 9 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.791, 0.189, 0.873, 0.218] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2778 | {
"bytes": "",
"path": "./images/40bf7303-ba39-44fe-b73f-ad3c9743c579_831a73c6-155d-4ce3-b1f4-03b69243735f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a 19-inch stainless steel kitchen sink with two equal bowls that could be shipped to my home and compare the top two cheapest.\nPrevious actions:\n[button] Departments -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.011, 0.3, 0.187, 0.323] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2779 | {
"bytes": "",
"path": "./images/cc643c1f-e73e-4e9f-abe9-5ee2d3b0a0dd_4f967b7a-9ed5-4a01-ac5a-4bfb8c5cf276.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Check the lowest price for a white 2017 certified pre owned Lexus Rx350 near 90012.\nPrevious actions:\n[LabelText] Certified Pre-Owned -> CLICK\n[combobox] Select Make -> SELECT: Lexus\n[combobox] Select Model -> SELECT: RX\n[textbox] Zip -> TYPE: 90012"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.601, 0.119, 0.748, 0.138] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2780 | {
"bytes": "",
"path": "./images/9ab66035-9569-4d5a-b1ca-09128cdd7456_e0f6b19c-2da6-4552-944e-8e375cf719be.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest Hawaii package for two adults from June 18 to 21, and the hotel must be near a beach, have a beachfront, hot tub, and pool, and provides towels.\nPrevious actions:\n[checkbox] Hot tub -> CLICK\n[checkbox] Pool -> CLICK\n[checkbox] Towels -> CLICK\n[button] Property style -> CLICK\n[checkbox] Beach -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.707, 0.205, 0.849, 0.215] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2781 | {
"bytes": "",
"path": "./images/c759aa6c-0738-4ac6-b03c-41d0f91ff4d3_19891f32-74d8-4b7e-9529-b6ad116c7002.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a SUV rental from Mar 31 (noon) to April 7, 2023 (noon) from Chicago O'hare Intl Airport, ORD and returning to same place with the lowest pay now price.\nPrevious actions:\n[span] , United States -> CLICK\n[span] , Chicago -> CLICK\n[link] Make a Reservation -> CLICK\n[button] Select My Car -> CLICK\n[link] All Vehicles (13) -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.5, 0.199, 0.929, 0.228] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2782 | {
"bytes": "",
"path": "./images/ab139e9d-eb99-47f7-8d0b-f93479fadadf_0d7ecbf2-34f6-44ad-8a78-48c3102e5df2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Track a bus using service number 5456165184.\nPrevious actions:\n[button] Check my bus -> CLICK\n[link] Track my bus -> CLICK\n[tab] Service Number -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.02, 0.212, 0.715, 0.255] in the image\nAnd my action is Action: TYPE\nValue: 5456165184"
}
]
|
mind2web_2783 | {
"bytes": "",
"path": "./images/5ea9ec16-845e-4a99-8848-fd96e8bad254_88177b5d-5f76-4638-84cf-a9abf0abec85.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find flights from Los Angeles to Miami for two people departing on July 1st and returning on July 7th.\nPrevious actions:\n[tab] Flights -> CLICK\n[button] Leaving from -> TYPE: Los Angeles, CA\n[button] Los Angeles (LAX - Los Angeles Intl.) California, ... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.359, 0.11, 0.641, 0.128] in the image\nAnd my action is Action: TYPE\nValue: Miami, FL"
}
]
|
mind2web_2784 | {
"bytes": "",
"path": "./images/92cfe78f-0385-4ef6-b829-ae34291e766f_769d15aa-5ed6-45e7-8caa-d271597da9d2.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find an LED TV below $1000.\nPrevious actions:\n[generic] Site Menu -> CLICK\n[link] TV & Home Theater -> CLICK\n[div] TV & Accessories -> CLICK\n[link] LED TV -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.025, 0.767, 0.192, 0.782] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2785 | {
"bytes": "",
"path": "./images/504c0c6b-7e78-4bfa-ae3f-00f8e59c3693_8bcb7868-5c9f-444e-8759-3c089e797034.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find a parking lot in Gloucester and book a ride from there to North Plymouth on April 28, 2:30 pm, view the map to understand the route better.\nPrevious actions:\n[button] Transit -> CLICK\n[link] Parking -> CLICK\n[link] Find Parking Lots -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.319, 0.481, 0.745, 0.517] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2786 | {
"bytes": "",
"path": "./images/36b86ab8-a448-46f7-813f-3e3b5c3d687c_99cd8c52-e44f-48d2-a670-27822e4ff213.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: find offer for a black Honda with vin number 1HGCM66543A064159 with 155000 millage near 49102. The car should be in good condition with no damage, 2+ keys and paid off.\nPrevious actions:\n[label] VIN -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.255, 0.188, 0.571, 0.21] in the image\nAnd my action is Action: TYPE\nValue: 1HGCM66543A064159"
}
]
|
mind2web_2787 | {
"bytes": "",
"path": "./images/f4dcbd09-45f3-47b5-a49d-36658d5b50ca_24f44f71-9d71-4647-a587-f4f33b5b3fb6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find tickets for Pizza making class in New York next month.\nPrevious actions:\n[combobox] Reservation type -> SELECT: Events\n[combobox] Event date -> SELECT: Next month\n[path] -> CLICK\n[button] Edit cuisine type filter -> CLICK\n[checkbox] Pizza -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.613, 0.465, 0.694, 0.509] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2788 | {
"bytes": "",
"path": "./images/4272e233-3440-4572-bd86-b3a2b22a4061_31ea9a5f-c903-46bb-a7cb-6b04c5af555a.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the most popular tours and attractions in Kyoto, Japan from May 25 with free cancellation option, check availability for 2 adults and 1 infant, and book.\nPrevious actions:\n[span] Attractions -> CLICK\n[span] Asia -> CLICK\n[div] Kyoto -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.083, 0.112, 0.354, 0.133] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2789 | {
"bytes": "",
"path": "./images/8b743c63-2a99-4c29-93ef-af920dab9535_89339d95-1d28-4d8e-bd50-7014518d77f1.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse monthly parking rates near the Museum of Modern Art.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.246, 0.204, 0.754, 0.219] in the image\nAnd my action is Action: TYPE\nValue: MOMA"
}
]
|
mind2web_2790 | {
"bytes": "",
"path": "./images/7685e8ad-3989-4316-85dd-746fac2956be_c909f54e-a1b0-4e7d-b89d-53df496da5ac.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for a recently posted part-time Job in Gamestop stores in Fresno, California, and apply.\nPrevious actions:\n[button] State / Province -> CLICK\n[span] -> CLICK\n[button] City -> CLICK\n[searchbox] City -> TYPE: fre\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.02, 0.619, 0.307, 0.658] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2791 | {
"bytes": "",
"path": "./images/8bfeeb54-beb9-4271-9436-fbd1a705efcd_241b0765-cc4d-4ce1-9b29-92cf7f2173c9.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the cheapest 2017 Honda Civic within 100 miles of 07470 which has a sun roof and black exterior color while excluding out of market vehicles\nPrevious actions:\n[button] Back to all categories -> CLICK\n[button] Make -> CLICK\n[listitem] Honda (116) Honda (116) -> CLICK\n[button] Back to all categories -> CLICK\n[button] Model -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.006, 0.521, 0.045, 0.555] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2792 | {
"bytes": "",
"path": "./images/1c6bfd10-4dcb-4a5c-bb2d-922ff9f20087_5ebb131c-9681-479f-ae2a-2c8d50b7e606.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Look for an English language book on roman empire history in the Kindle store released in the last 90 days, it should be displayed according to its latest publication date, and add the top result to the shopping list.\nPrevious actions:\n[button] Open Menu -> CLICK\n[link] Kindle E-readers & Books -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.0, 0.281, 0.285, 0.304] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2793 | {
"bytes": "",
"path": "./images/e9f5f0d0-7241-4a28-b387-c65a0ce52a61_f1d21f88-e302-42ae-8d0c-0144616650fc.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for a rental car in Miami, FL for pick up at the airport and drop off at a different location within the same city.\nPrevious actions:\n[link] Search for cars -> CLICK\n[svg] -> CLICK\n[tab] Different drop-off -> CLICK\n[textbox] Pick-up location -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.241, 0.193, 0.38, 0.24] in the image\nAnd my action is Action: TYPE\nValue: Miami Airport"
}
]
|
mind2web_2794 | {
"bytes": "",
"path": "./images/37564222-bb58-4a55-b47b-e9ffbbc1d160_c62fa753-fdf3-4a97-a464-d6e1a2d7c20f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the results of the most recent NFL games.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.265, 0.078, 0.286, 0.089] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2795 | {
"bytes": "",
"path": "./images/f3bf7fe9-6987-4153-81b4-4b51fe25bbbc_b47b0fbe-e5bf-4cb4-a560-93d4d86a1f35.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Search for rental cars in Seattle, WA and filter the results by the Best score.\nPrevious actions:\n[link] Search for cars -> CLICK\n[textbox] Pick-up location -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.241, 0.133, 0.568, 0.165] in the image\nAnd my action is Action: TYPE\nValue: Seattle"
}
]
|
mind2web_2796 | {
"bytes": "",
"path": "./images/7219145b-ada1-480e-a8ea-f4fe164ca84a_d7618269-d378-4b6e-9124-9f8558d304d6.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Book a one way ticket from Faro to Bournemouth leaving on 30th April, with a value fare, for a passenger named Mr. Joe Bloggs. Don't select now and only take 1 small bag onboard.\nPrevious actions:\n[button] Continue for $ 148 . 16 -> CLICK\n[button] Continue with Value fare -> CLICK\n[button] Log in later -> CLICK\n[button] - -> CLICK\n[div] Mr -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.184, 0.7, 0.353, 0.737] in the image\nAnd my action is Action: TYPE\nValue: Joe"
}
]
|
mind2web_2797 | {
"bytes": "",
"path": "./images/980d35af-6c00-4d6c-94cd-0c41e0fabb76_24f70490-eff7-4c67-aaaa-e72120ee5528.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Browse mens Timberland boots in size 9 and under $100 and filter by lowest price.\nPrevious actions:\n[combobox] Search for anything -> TYPE: mens timberland boots\n[button] Search -> CLICK\n[link] 9 - apply US Shoe Size filter -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.128, 0.553, 0.184, 0.571] in the image\nAnd my action is Action: TYPE\nValue: 100"
}
]
|
mind2web_2798 | {
"bytes": "",
"path": "./images/122af0dc-9e4e-4c5a-98ad-5c4d02f32284_2c7c5fe2-1b57-449c-83f0-eb79a096739f.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find the next available bus from Chicago to Ann Arbor.\nPrevious actions:\n[textbox] From (type text or use the arrow keys) -> TYPE: Chicago"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.078, 0.487, 0.137, 0.503] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_2799 | {
"bytes": "",
"path": "./images/3f0988e0-e3a4-4dd7-a89f-482175a474a8_ee36e538-a5c9-46f4-a19d-7fb9f3fc9b3c.png"
} | [
{
"from": "human",
"value": "<image>\nImagine that you are imitating humans doing web navigation for a task step by step. At each stage, you can see the webpage like humans by a screenshot and know the previous actions before the current step decided by yourself through recorded history. You need to decide on the first following action to take. You can click an element with the mouse, select an option, or type text with the keyboard. (For your understanding, they are like the click(), select_option() and type() functions in playwright respectively) One next step means one operation within the three.\nPlease pinpoint the bounding box coordinates of the element’s region that I should click in order to complete the following instruction: Find Wheelchair accessible parking for April 09 event in Barclays Center that allows entry after 10am\nPrevious actions:\n[textbox] Search for parking -> TYPE: Barclays Center\n[li] Barclays Center, Atlantic Avenue, Brooklyn, NY, US... -> CLICK\n[textbox] Select Event Date -> CLICK\n[gridcell] Sun Apr 09 2023 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.337, 0.379, 0.568, 0.399] in the image\nAnd my action is Action: CLICK"
}
]
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.