id
stringlengths 10
13
| image
dict | conversations
listlengths 2
2
|
|---|---|---|
mind2web_4200 | {
"bytes": "",
"path": "./images/edbac1c3-5409-48b0-a0ac-402a4900c59f_3be026ae-9dc4-4f3a-aefe-230af68e72dd.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 planned service alerts for the subway red line\nPrevious actions:\n[link] subway Subway Lines -> CLICK\n[span] Red Line -> CLICK\n[link] Alerts 8 alerts -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.125, 0.399, 0.295, 0.444] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4201 | {
"bytes": "",
"path": "./images/3e9d6144-e92b-4fb0-b634-48bf3eb5090b_31af69cc-8439-4cfd-8d2b-1a335a0e1e5a.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 a trip from Greenport to Oyster Bay Branch, starting with train and ending via bus with less than 1/2 mile walk.\nPrevious actions:\n[searchbox] From -> TYPE: Greenport\n[listitem] Greenport, NY, USA -> CLICK\n[searchbox] To -> TYPE: Oyster Bay\n[listitem] Oyster Bay, NY, USA -> CLICK\n[button] Open Travel Preferences modal. -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.396, 0.255, 0.61, 0.277] in the image\nAnd my action is Action: SELECT\nValue: Train"
}
]
|
mind2web_4202 | {
"bytes": "",
"path": "./images/099a9da4-c8db-4900-ada2-76600f3655a4_d1da3a0f-8824-4fcf-ba81-24debe082563.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 list of baby products that are on sale and under 10 dollars.\nPrevious actions:\n[link] BABY -> HOVER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.519, 0.121, 0.727, 0.145] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4203 | {
"bytes": "",
"path": "./images/74f01011-9bcd-433b-8405-975ca5c3f356_76a9fd32-80ff-45ce-879a-aa7d959c9b62.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 address and store hours for the Armageddon Shop record store in Boston.\nPrevious actions:\n[button] Community -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.564, 0.247, 0.728, 0.279] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4204 | {
"bytes": "",
"path": "./images/1f128c19-3093-4c49-bfc7-13589aa8e88a_e3b4f654-b33f-429f-8327-feb0da8ca5e9.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 a Hasbro Hulk action figure manufactured in 1990 with the lowest price + shipping.\nPrevious actions:\n[link] Toys -> HOVER\n[link] Action Figures -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.378, 0.207, 0.503, 0.341] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4205 | {
"bytes": "",
"path": "./images/1a2befd0-5e90-4bed-81b5-8ee0a93873df_c8af097d-59f1-4eae-ac13-da33e869dd8e.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 RPG video games.\nPrevious actions:\n[button] Main Menu -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.0, 0.242, 0.291, 0.285] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4206 | {
"bytes": "",
"path": "./images/1ba150cb-3b4a-4f0a-bff0-b448c78608ae_90a2701a-0940-4f95-a93c-d61d8a2cecaa.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 hotel deals in Las Vegas for four adults starting on May 17 and ending on May 20, and if deal is not available, set an alert for the same.\nPrevious actions:\n[textbox] What type of deals? -> CLICK\n[div] Hotels -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.303, 0.122, 0.492, 0.174] in the image\nAnd my action is Action: TYPE\nValue: las vegas"
}
]
|
mind2web_4207 | {
"bytes": "",
"path": "./images/b1eb6602-3aa7-40ee-8968-69d83e7ef21c_92169b81-9840-4ae7-af42-73477badeb33.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 newest silver-colored Lexus SUV with a black interior and backup camera to purchase which has been made between 2022-2023 and is within 50 miles of zip 10017.\nPrevious actions:\n[span] Silver -> CLICK\n[p] Black -> CLICK\n[p] Lexus -> CLICK\n[p] Backup Camera -> CLICK\n[combobox] Select Sort Order -> SELECT: Newest first (by car year)"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.266, 0.194, 0.617, 0.437] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4208 | {
"bytes": "",
"path": "./images/c2a17420-ceb4-4324-ae8f-60cf845a144b_1b6cc686-4b86-41f5-9df2-290404ccfc53.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 Canyon de Chelly schedule calendar.\nPrevious actions:\n[link] FIND A PARK -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.211, 0.13, 0.789, 0.155] in the image\nAnd my action is Action: TYPE\nValue: Canyon de Chelly"
}
]
|
mind2web_4209 | {
"bytes": "",
"path": "./images/41cd71cb-cae5-41c8-abe8-67e42fabd4a5_656ed1ca-1b96-4f94-9342-a57e054a3cdd.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 details of Grand National Parks tour.\nPrevious actions:\n[button] DEALS -> CLICK\n[link] VACATIONS & RAIL TOURS Train vacation packages thr... -> CLICK\n[img] -> CLICK\n[link] Close -> CLICK\n[button] Itinerary -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.359, 0.454, 0.424, 0.52] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4210 | {
"bytes": "",
"path": "./images/e7fbd3a3-d583-46b9-ad7e-3f7b765fc311_8b0ee93f-8fc6-4664-930a-4f58525661ba.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 cheap flights from NYC to London on 23rd of April for students over 18 years.\nPrevious actions:\n[tab] One-way -> CLICK\n[button] 1 adult -> CLICK\n[button] Increment -> CLICK\n[path] -> CLICK\n[textbox] Flight destination input -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.355, 0.093, 0.432, 0.115] in the image\nAnd my action is Action: TYPE\nValue: new york"
}
]
|
mind2web_4211 | {
"bytes": "",
"path": "./images/39b037ac-0a11-4b05-8919-b4f9863fd0cd_a0c205cb-1a8c-44e3-af38-ff210c95571e.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 review of Prometheus movie.\nPrevious actions:\n[path] -> CLICK\n[tab] MOVIES -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.323, 0.121, 0.677, 0.141] in the image\nAnd my action is Action: TYPE\nValue: Prometheus"
}
]
|
mind2web_4212 | {
"bytes": "",
"path": "./images/8e849b85-5acc-4d26-ad5e-d24ad24343df_05a173a8-2088-4da9-97e3-f8988811b5b0.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 parking spot for James SMith at Stewart Hotel in New York for 2 hours. The street address is 133 st avenue in New York. Zip code is 10001 and phone number is 888888888. The email address is [email protected]. Employer's name is Gua AB.\nPrevious actions:\n[textbox] First Name -> CLICK\n[textbox] First Name -> TYPE: James\n[textbox] Last Name -> TYPE: SMith\n[textbox] Address1 -> TYPE: 133 st avenue\n[textbox] City Name -> TYPE: New York"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.289, 0.549, 0.501, 0.58] in the image\nAnd my action is Action: SELECT\nValue: New York"
}
]
|
mind2web_4213 | {
"bytes": "",
"path": "./images/486bdb13-16c5-4a53-8566-a60caaf94a73_898bc6da-8851-414f-9e66-eacba595b118.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 GoBites Uno Spork in the color magenta and have it delivered to a store in Seattle, WA. Checkout with default address, and use credit number 123456789, CVV 123, expire 01, 2024\nPrevious actions:\n[searchbox] Search -> TYPE: gobites uno spork\n[button] Search -> CLICK\n[img] humangear GoBites Uno Spork 0 -> CLICK\n[button] Color: Magenta -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.887, 0.463, 0.956, 0.473] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4214 | {
"bytes": "",
"path": "./images/b83120d9-5892-4e8f-b4b9-346cc07827a7_35dd7c87-f653-4de6-a617-d3503d0bdc73.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: Create a playlist and name it \"Dirty\" and add 5 Doja Cat songs.\nPrevious actions:\n[button] Search -> CLICK\n[button] Add -> CLICK\n[button] ADD TRACK -> CLICK\n[textbox] Search -> TYPE: Doja Cat\n[button] Search -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.662, 0.321, 0.688, 0.34] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4215 | {
"bytes": "",
"path": "./images/ddd935d4-9c28-4e64-bb4f-91ad1cb974dc_94ea2d0e-1ab8-4d5f-bdd8-a9735cfc485e.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: See in the Men's sale if any L-sized t-shirt in blue color is available or not, if available, add one to the cart choose pick in store for zip 10005.\nPrevious actions:\n[heading] Size -> CLICK\n[label] L -> CLICK\n[heading] Color -> CLICK\n[label] BLACK -> CLICK\n[svg] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.05, 0.464, 0.266, 0.7] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4216 | {
"bytes": "",
"path": "./images/0c7a69f9-989d-4899-a3fe-94c952859007_5612cccb-4e39-483a-8b5b-9d4f9261f5b9.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 Chicago to London on 20 April and return on 23 April.\nPrevious actions:\n[textbox] From -> TYPE: Chicago\n[a] CHI - Chicago, IL -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.381, 0.372, 0.62, 0.391] in the image\nAnd my action is Action: TYPE\nValue: London"
}
]
|
mind2web_4217 | {
"bytes": "",
"path": "./images/cf89b0ae-39ca-4451-80df-260d46c62f21_3253cf50-b912-4446-9ca0-00ff7813f42a.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 hotel in Ohio From July 2nd to July 8th for 2 adults.\nPrevious actions:\n[textbox] Going to -> TYPE: Ohio\n[button] Ohio United States -> CLICK\n[button] Check-in March 18, 2023 -> CLICK\n[button] Next month -> CLICK\n[button] Next month -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.959, 0.122, 0.984, 0.135] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4218 | {
"bytes": "",
"path": "./images/ca049641-9721-4593-95c5-a47e22365b5b_45f14dab-05eb-4113-a9ba-6dd6aad8acd6.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\n[heading] Fuel Type -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.131, 0.251, 0.277, 0.266] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4219 | {
"bytes": "",
"path": "./images/06497906-8b76-4367-a1b3-ebc8238bd470_6f204b33-e51a-4ce0-ae28-d22278162aaa.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: Choose a lowest priced hybrid SUV car to pick up from Bangkok downtown on May 24 at 9:30 am and drop off on May 28, at 9 am.\nPrevious actions:\n[div] Thu, Apr 20 -> CLICK\n[checkbox] 24 May 2023 -> CLICK\n[checkbox] 28 May 2023 -> CLICK\n[combobox] Pick up time -> SELECT: 9:30 AM\n[combobox] Drop off time -> SELECT: 9:00 AM"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.853, 0.094, 0.923, 0.123] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4220 | {
"bytes": "",
"path": "./images/b20e1dc4-651b-46e1-8470-16250657f2a8_a82c1270-924d-4758-86cd-30ba60260eb9.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 SUV in Brooklyn for 1 day.\nPrevious actions:\n[tab] Same drop-off -> CLICK\n[button] End date -> CLICK\n[button] May 22, 2023 -> CLICK\n[svg] -> CLICK\n[img] SUV -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.073, 0.128, 0.23, 0.152] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4221 | {
"bytes": "",
"path": "./images/c9f65ae8-bd67-4a83-82d7-d42587e34e98_d4f1c897-c5aa-4cb7-afa2-3ddd845df114.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 parking space in Houston. Name: James Smith, Email: [email protected], phone: 8888888888. Address: 123rd st.\nPrevious actions:\n[link] Rent My Parking Space -> CLICK\n[textbox] First Name * -> TYPE: James"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.212, 0.799, 0.787, 0.82] in the image\nAnd my action is Action: TYPE\nValue: Smith"
}
]
|
mind2web_4222 | {
"bytes": "",
"path": "./images/84f19aba-ad0a-46db-84bb-c279b5353b8a_fe69325d-0689-46ae-b411-dbb199d259aa.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 cafes that have outdoor seating and is dog friendly.\nPrevious actions:\n[textbox] Find -> TYPE: cafe\n[span] Cafe -> CLICK\n[button] All -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.031, 0.301, 0.066, 0.32] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4223 | {
"bytes": "",
"path": "./images/d7c3103a-c195-4503-ab20-ecae4d4ce419_23f591fd-977a-437a-931d-4be0a372db4f.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 motorcycle toll fee for the Queens midtown tunnel.\nPrevious actions:\n[link] Fares & Tolls -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.133, 0.467, 0.5, 0.493] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4224 | {
"bytes": "",
"path": "./images/b5d47068-b773-4061-b7ba-17bd25e88e06_92c31707-5c0d-450e-a9bd-b0290f28f907.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: Save two deals and offers for US.\nPrevious actions:\n[button] Deals -> HOVER\n[button] Deals -> CLICK\n[link] US Deals -> CLICK\n[button] Save Now -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.538, 0.018, 0.598, 0.026] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4225 | {
"bytes": "",
"path": "./images/e92a2c89-3310-434b-9543-a0d896881bb9_7e70b73f-5b14-457e-b4cc-532742d72dcc.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 premium car in Brooklyn for a day.\nPrevious actions:\n[link] Rent A Car -> CLICK\n[button] Pick-up -> TYPE: Brooklyn\n[button] Brooklyn New York, United States -> CLICK\n[button] Search -> CLICK\n[input] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.031, 0.164, 0.045, 0.174] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4226 | {
"bytes": "",
"path": "./images/7bda9645-0b5f-470a-8dd7-6af0bff4da68_0bc81932-85d7-467f-8ef7-294f55118587.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 for pickup restaurant available in Boston, NY on March 18, 5pm with just one guest\nPrevious actions:\n[button] 18 -> CLICK\n[combobox] Time -> SELECT: 5:00 PM\n[svg] -> CLICK\n[span] 2 guests -> CLICK\n[combobox] Size -> SELECT: 1 guest"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.399, 0.691, 0.525, 0.732] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4227 | {
"bytes": "",
"path": "./images/2ce0a80e-a049-434d-8b99-8343d2a0b21d_8a1d16e9-9527-42fd-9a08-6a0e9d39c051.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:\n[button] Explore -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.315, 0.033, 0.44, 0.051] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4228 | {
"bytes": "",
"path": "./images/813e47ec-6304-42c5-82d4-1fc461247965_9b7e228b-1dc4-478c-9137-946f5ef3034c.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 set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[button] Sort Best match -> CLICK\n[radio] Price: low to high -> CLICK\n[path] -> CLICK\n[span] -> CLICK\n[path] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.656, 0.183, 0.966, 0.228] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4229 | {
"bytes": "",
"path": "./images/df3b7cd4-526e-453b-9114-c0db1b3ed5ea_9294ad81-1046-46ae-a950-85a3a34e1b77.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 Dining Room Sets under furniture and filter the results to show only items availble under the Buy It Now format.\nPrevious actions:\n[link] Home & Garden -> CLICK\n[button] Furniture -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.024, 0.556, 0.184, 0.57] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4230 | {
"bytes": "",
"path": "./images/1f128c19-3093-4c49-bfc7-13589aa8e88a_cb9d3a61-b898-4330-8767-fb2a56c37b64.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 a Hasbro Hulk action figure manufactured in 1990 with the lowest price + shipping.\nPrevious actions:\n[link] Toys -> HOVER\n[link] Action Figures -> CLICK\n[img] Hasbro -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.915, 0.274, 0.969, 0.295] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4231 | {
"bytes": "",
"path": "./images/020bc054-a829-4af5-8f0a-6efce012c7ac_72174279-0b65-4da3-8ed8-69a5f4bd03cd.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 the number 4 ranked board game on the geekmarket.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.123, 0.011, 0.183, 0.035] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4232 | {
"bytes": "",
"path": "./images/cf361c84-6414-4b05-a7a1-77383997150a_31ddff52-15df-4d0d-916c-18e1fb240ea2.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 an SUV with an additional driver and wifi for pick up in any rental location near Washington regional airport on June 1, 11 am, and drop off at Washington international airport on June 2, 11 am, and pay for the booking instantly.\nPrevious actions:\n[button] Locations -> HOVER\n[link] Find a Location -> CLICK\n[textbox] Search by Airport, City, Zip, Address or Attractio... -> TYPE: washington\n[span] Washington County Regional Apo -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.748, 0.302, 0.905, 0.326] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4233 | {
"bytes": "",
"path": "./images/3f0988e0-e3a4-4dd7-a89f-482175a474a8_d194ee95-87f0-4ad2-a6ce-d06cf89fec9c.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"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.073, 0.117, 0.78, 0.125] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4234 | {
"bytes": "",
"path": "./images/2742f638-cf66-4c72-a6a6-69f2a12bc269_4672b855-b26c-4b81-9010-18d6ec210c9e.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 on May 9 and return on May 16 from Tel Aviv to Venice with plus type fare option.\nPrevious actions:\n[textbox] From -> TYPE: TEL AVIV"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.523, 0.157, 0.715, 0.172] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4235 | {
"bytes": "",
"path": "./images/f9062def-8361-48df-849c-4d7dbc1e11d1_64c3c386-4170-4ca4-a34b-5e3c589da638.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 trade in value for PS4 console\nPrevious actions:\n[searchbox] Find values for games and more -> TYPE: PS4\n[button] SEARCH -> CLICK\n[link] Filter -> CLICK\n[generic] Refine by Category: Consoles & Hardware -> CLICK\n[link] PlayStation 4 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.203, 0.033, 0.378, 0.057] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4236 | {
"bytes": "",
"path": "./images/8865ca64-0df2-4e3f-905d-a9e07e1eeb68_9331a1b5-54f8-4de6-acd5-dd60c9a19d53.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\n[button] Search nearest REI stores -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.217, 0.141, 0.318, 0.155] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4237 | {
"bytes": "",
"path": "./images/3eae65d9-7778-4cf2-bc3d-f666b5e43bce_2e6cf0b7-800a-42f3-af4a-d2f3c85a6bf5.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: Notify me about availability for 2 guests on april 17 at the High Tide restaurant\nPrevious actions:\n[textbox] Search restaurants, cuisines, etc. -> TYPE: high tide\n[heading] High Tide -> CLICK\n[div] Fri., Apr. 21 -> CLICK\n[button] April 17, 2023. -> CLICK\n[combobox] Guests -> SELECT: 2 Guests"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.012, 0.313, 0.119, 0.331] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4238 | {
"bytes": "",
"path": "./images/3a231c03-d038-4b61-b5a2-685b77d9920e_9e8314a0-1e1e-4db1-9e85-422dfa0bb165.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 the bag charges for the passenger James Son for the flight with the confirmation number 10000002\nPrevious actions:\n[tab] TRAVEL INFO -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.275, 0.091, 0.343, 0.101] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4239 | {
"bytes": "",
"path": "./images/d22ce493-c49c-43f7-939c-4a429797c2a3_a686b3cc-e59b-43b8-bb1e-22e1bef857da.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 me a flight from BWI to NYC for 2 for August 2nd-August 7th\nPrevious actions:\n[button] New York, NY, US (NYC - All Airports) -> CLICK\n[textbox] Depart -> CLICK\n[button] Move forward to switch to the next month. -> CLICK\n[button] Move forward to switch to the next month. -> CLICK\n[button] Wednesday, August 2, 2023 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.361, 0.229, 0.391, 0.246] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4240 | {
"bytes": "",
"path": "./images/5a15ea92-571d-4a45-ad18-5b4eddbc70a6_3dd8bf82-b783-4ede-b42a-0b632c8cb365.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 lowest priced plus size one piece active swimsuit in color black.\nPrevious actions:\n[link] Women -> HOVER\n[link] Swimwear -> CLICK\n[link] Women's Plus -> CLICK\n[div] Color -> CLICK\n[link] Black (294) -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.707, 0.213, 0.877, 0.231] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4241 | {
"bytes": "",
"path": "./images/3d77584f-9074-46db-bd1e-086a506b54d3_a5338369-622d-496d-b922-ce73b9e1b5df.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 third-party certified front-wheel driving automatic white car for sale near Tampa, Florida with online paperwork and no accidents, confirm availability with my details.\nPrevious actions:\n[checkbox] Online Paperwork (4) -> CLICK\n[span] Vehicle History -> CLICK\n[checkbox] No Accidents (4) -> CLICK\n[combobox] Sort By: -> SELECT: Price - Lowest\n[link] Confirm Availability for Used 2019 Buick Encore Pr... -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.357, 0.104, 0.494, 0.124] in the image\nAnd my action is Action: TYPE\nValue: James"
}
]
|
mind2web_4242 | {
"bytes": "",
"path": "./images/24de7f7d-f3f0-41a6-a578-e35b513b46e5_f49b8bab-88cc-4b73-a5a1-d63b597c4b0d.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 Maytag electric dryers that are at least 7.3 cubic foot costing less than $1000 that are available in store at Montgomery, Illinois with zip code 60538.\nPrevious actions:\n[button] COLUMBUS, OH -> CLICK\n[path] -> CLICK\n[textbox] Zip Code -> TYPE: 60538"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.183, 0.163, 0.335, 0.184] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4243 | {
"bytes": "",
"path": "./images/8308d10f-3904-473a-a186-c6b8f939f018_3107856a-910f-40db-a9d0-abe314f18545.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 longest private sightseeing trip of India in the month of June\nPrevious actions:\n[textbox] Where to? -> TYPE: India\n[button] India Asia -> CLICK\n[button] Next -> CLICK\n[path] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.668, 0.323, 0.705, 0.343] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4244 | {
"bytes": "",
"path": "./images/4c623130-32db-4cc8-928a-68b0bc816efc_ab0c775c-0a0a-4b43-85ea-e348652a38da.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 artist Mark Knight from London and follow him and add his most liked track to next up.\nPrevious actions:\n[searchbox] Search -> TYPE: Mark Knight\n[button] Search -> CLICK\n[link] Mark Knight -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.773, 0.302, 0.838, 0.326] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4245 | {
"bytes": "",
"path": "./images/86ea50f5-1310-456e-97bf-799d8eb1896b_12e7f7fd-5ca7-42df-8962-903e1a49e4fb.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 NFL Passing yards players stats.\nPrevious actions:\n[link] National Football League NFL -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.742, 0.035, 0.775, 0.052] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4246 | {
"bytes": "",
"path": "./images/f8027aa8-c193-47c8-a97b-432836093939_f783514e-6e62-4f91-bf42-00e2edb90295.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 hotels in Las Vegas, NV that offer free airport shuttle service.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.006, 0.051, 0.181, 0.068] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4247 | {
"bytes": "",
"path": "./images/f863168b-1d7e-4f51-9681-79891abc4b45_0a904ba2-dca6-4ad1-8af2-f6568ea6d8eb.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 park in the National Park System that has a Junior Ranger Program for kids.\nPrevious actions:\n[link] FIND A PARK -> CLICK\n[link] Search by Activity or Topic -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.359, 0.174, 0.641, 0.193] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4248 | {
"bytes": "",
"path": "./images/9c9e89c1-fdb9-424c-b544-b9fd2f1ef46e_5968648f-ed49-45e3-903a-229b30081048.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 Limited Time Offers available in the Kids section and filter by size, 11-12Y(150).\nPrevious actions:\n[link] KIDS -> CLICK\n[link] Limited-Time Offers -> CLICK\n[gridcell] Size -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.073, 0.3, 0.165, 0.312] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4249 | {
"bytes": "",
"path": "./images/17fffbee-e41b-46e4-ab75-675b263ca7b7_3f694618-f0a3-47d5-98c5-024c53562900.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 power supply unit with at least 600W power output.\nPrevious actions:\n[searchbox] Search Site -> TYPE: 600w power supply"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.496, 0.011, 0.546, 0.035] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4250 | {
"bytes": "",
"path": "./images/2177b546-5718-478b-8535-bc37975b0d0c_fb3aafe7-6077-4b37-9cfc-65b1e614cdea.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 2 hot seat VIP tickets through email id [email protected] for Adele's concert in Las Vegas on the last weekend of June.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.164, 0.149, 0.782, 0.177] in the image\nAnd my action is Action: TYPE\nValue: adele"
}
]
|
mind2web_4251 | {
"bytes": "",
"path": "./images/3d83f3de-58f2-4aba-9b02-4a230d35a4ef_ffd3f2e7-1bd0-4bd4-b057-e7b05e92d656.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 adventure game available for early access.\nPrevious actions:\n[link] Categories -> HOVER\n[link] Early Access -> CLICK\n[div] Narrow By -> CLICK\n[link] Adventure -> CLICK\n[generic] TOP RATED -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.531, 0.732, 0.632, 0.748] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4252 | {
"bytes": "",
"path": "./images/34e13beb-0235-41d4-b108-137cc7480904_3abb0c61-a81b-4dc7-ac70-d88eb176a529.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 parking spot for a standard car near 66 Perry St., New York, from April 20, 5:30 pm to April 21, 5:30 am.\nPrevious actions:\n[link] 05:30AM -> CLICK\n[button] SEARCH -> CLICK\n[span] Distance -> CLICK\n[link] Price -> CLICK\n[button] Book now -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.378, 0.11, 0.622, 0.144] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4253 | {
"bytes": "",
"path": "./images/8eae88ef-9641-43c6-be6d-f8abc96d99fa_9c7ed1f9-73cf-40b2-807e-d0e4aa0cd853.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 expensive Sony controller compatible with PS5 with free shipping and add it to my cart.\nPrevious actions:\n[link] Gaming & VR -> HOVER\n[link] PS5 Accessories -> CLICK\n[generic] Controller -> CLICK\n[span] Sony -> CLICK\n[button] APPLY -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.025, 0.326, 0.158, 0.334] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4254 | {
"bytes": "",
"path": "./images/3358dffd-3673-435b-bfcb-cb242a2c622c_61a9ea08-e8d9-4584-affd-51e292f094e5.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] From (type text or use the arrow keys) -> TYPE: Houston\n[span] Houston, TX -> CLICK\n[textbox] To (type text or use the arrow keys) -> TYPE: Dallas\n[div] Dallas, TX -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.58, 0.211, 0.721, 0.228] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4255 | {
"bytes": "",
"path": "./images/712d9d7f-d7ee-4554-affa-133449231ae4_1b19b03c-7423-46e6-abea-ab1bb37a520b.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 latest medical audiobook on complementary medicine for under 20 dollars and add the top book to the cart.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.021, 0.11, 0.129, 0.137] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4256 | {
"bytes": "",
"path": "./images/8e4dbb21-de6c-4b9a-8bd1-97fc6b1fe3c0_2f874e77-6f98-43bf-a476-bb69382c7197.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 wedding venue in Venice Beach California in June for 100 guests.\nPrevious actions:\n[button] Find & Reserve -> CLICK\n[link] Book Meetings & Events -> CLICK\n[heading] Weddings -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.68, 0.48, 0.943, 0.489] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4257 | {
"bytes": "",
"path": "./images/74b456b6-0e62-429f-b13c-45861f2cdf82_0cd3a314-e9db-447c-ac17-e07b23307fca.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[button] City -> CLICK\n[span] -> CLICK\n[button] Hiring Type -> CLICK\n[span] -> CLICK\n[combobox] Sort by -> SELECT: Most recent"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.309, 0.202, 0.792, 0.221] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4258 | {
"bytes": "",
"path": "./images/4786982f-25f5-4bf8-bb91-522656489f63_d8a64f26-d3fa-47cc-a614-7ac555797a95.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[span] 25 -> CLICK\n[svg] -> CLICK\n[svg] -> CLICK\n[checkbox] 5 June 2023 -> CLICK\n[div] 1 days -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.82, 0.204, 0.927, 0.232] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4259 | {
"bytes": "",
"path": "./images/35cf31d3-c88d-45fe-9959-4cf1de72bc7d_d0fa9c16-fbc1-4ab6-bdc5-13758977249b.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 for trending women sports bras and add 3 trending black bras to Wishlist.\nPrevious actions:\n[link] Sports Bras -> CLICK\n[div] Color -> CLICK\n[link] Refine by color: Black -> CLICK\n[button] Add to Wish List -> CLICK\n[button] Add to Wish List -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.925, 0.17, 0.947, 0.184] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4260 | {
"bytes": "",
"path": "./images/2a45ede7-6449-40b2-b032-149ddbe205a9_753df684-6110-40eb-88b5-aae9df30ed15.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: Contact Yeah You Right Events who are the organisers of the Food Fight 2023 event being held in New Orleans on May 25th to ask a question about the event\nPrevious actions:\n[combobox] autocomplete -> TYPE: New Orleans\n[div] LA, USA -> CLICK\n[button] Food & Drink -> CLICK\n[div] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.216, 0.452, 0.308, 0.475] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4261 | {
"bytes": "",
"path": "./images/e12f51f6-c8c5-4a68-9586-d77927bca79c_db4941b4-a391-4fff-911c-fd74052dfd3c.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 Tesla Shop Gift Card for April May with the email [email protected] to my cart\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.705, 0.054, 0.753, 0.081] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4262 | {
"bytes": "",
"path": "./images/eebf3f55-1a4d-4cdf-81c1-2fa3002bed6d_d153d7e1-bde1-467f-a08a-77052c38a054.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 Keen branded new pair of women's hiking shoes in the color brown, number 9, available in Columbus, Ohio store, average rating must be above 4.\nPrevious actions:\n[svg] -> CLICK\n[label] Brown -> CLICK\n[svg] -> CLICK\n[label] 9 -> CLICK\n[label] Available in Store -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.034, 0.547, 0.062, 0.559] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4263 | {
"bytes": "",
"path": "./images/274571ea-fc2f-4353-86ba-00ecb112d6d2_b6481fae-c97a-4af4-a416-ccd071c8cdc1.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 multi-colored fillable eggs for easter eggs made from polypropylene priced between 5 to 10 dollars for pick-up from Barboursville, zip 25504.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.004, 0.042, 0.041, 0.065] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4264 | {
"bytes": "",
"path": "./images/6e98e331-c80b-4316-b332-af76c4cb2440_a1d7fbd9-6bde-48f1-aa51-307d0fcac7a4.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[div] Product Type -> CLICK\n[link] Polos -> CLICK\n[div] Size -> CLICK\n[link] M -> CLICK\n[span] Now Trending -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.842, 0.192, 0.947, 0.208] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4265 | {
"bytes": "",
"path": "./images/1fefdb27-882b-481b-97e2-720f4d2338a3_e7072a8a-6a01-4c81-a4f3-9a80483927f5.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 activities in Phuket, Thailand.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.491, 0.706, 0.501, 0.711] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4266 | {
"bytes": "",
"path": "./images/fdcac1e8-1dd0-4846-b2cf-16d916ea9e17_42ebb272-99de-4d4e-b103-5062fbbb61ac.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 tickets for los angeles kings this weekend\nPrevious actions:\n[textbox] Search for artists, teams or venues... -> TYPE: los angeles kings\n[option] Los Angeles Kings -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.627, 0.31, 0.65, 0.323] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4267 | {
"bytes": "",
"path": "./images/fc552b69-feb8-4951-bf67-725071bf8c8a_f95e947b-7409-4178-aa26-31b38f194d40.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 fasted flexible direct flights from New York to Tokyo on June 1, between 6 to 12 pm departure, and from Tokyo to New Delhi on June 5.\nPrevious actions:\n[span] Where to? -> TYPE: NEW DELHI\n[b] DEL -> CLICK\n[button] Choose departure date -> CLICK\n[checkbox] 5 June 2023 -> CLICK\n[button] Search -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.07, 0.37, 0.34, 0.396] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4268 | {
"bytes": "",
"path": "./images/0dd6fbb7-4236-47f7-a69c-30f0836b76c3_3de56dba-079d-48d7-ae00-1612cbd66ca0.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: See the price trends of used Tesla cars from August 1, 2022, to January 31, 2023, and compare the trend with the Cargurus index.\nPrevious actions:\n[menuitem] Research -> HOVER"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.28, 0.054, 0.387, 0.072] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4269 | {
"bytes": "",
"path": "./images/1efdcd9d-ebc6-4bb7-8823-e54dfe25f409_f2e91900-b7dc-48c1-86c8-0add81412717.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 reservation for three guest on April 5th, 5pm in Alinea restaurant, Chicago, IL\nPrevious actions:\n[button] Search -> CLICK\n[textbox] Search -> TYPE: Alinea\n[span] Chicago, IL - Lincoln Park -> CLICK\n[i] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.704, 0.169, 0.908, 0.204] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4270 | {
"bytes": "",
"path": "./images/a6372f23-f462-4706-8455-5b350c46d83c_b36d2bf4-1700-4742-a245-e46c85973a6f.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 winery tour in Napa Valley in a winery which serves Mediterranean cuisine with wine testing for 4 guests on April 15, 10 am in a outdoor setup.\nPrevious actions:\n[button] Submit -> CLICK\n[button] Open additional search filters -> CLICK\n[checkbox] Outdoors -> CLICK\n[checkbox] Wine tasting -> CLICK\n[button] Update search -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.038, 0.419, 0.141, 0.452] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4271 | {
"bytes": "",
"path": "./images/56d210ec-22eb-4b3f-ba76-ee531403701a_e11c9f8b-0365-4908-b2cd-c64e9f0e9b7d.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: Use the \"Meetings & Events\" section of the website to browse locations for a business meeting for one room and 20 guests in Boston from May 30th to June 1st.\nPrevious actions:\n[gridcell] Thu, Jun 1, 2023 -> CLICK\n[label] Purpose of your event -> CLICK\n[li] Business -> CLICK\n[textbox] Guest rooms -> TYPE: 1\n[textbox] Event space -> TYPE: 20"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.663, 0.3, 0.959, 0.335] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4272 | {
"bytes": "",
"path": "./images/2159d768-6657-40af-b336-ad5726fec1e2_37493ad9-bdcf-4e45-a8bc-de60d4dc7fde.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 to my wishlist the top rated JRPG game.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.006, 0.453, 0.06, 0.467] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4273 | {
"bytes": "",
"path": "./images/813e47ec-6304-42c5-82d4-1fc461247965_6197c144-0a0c-4e0d-abcf-1b380989feed.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 set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.09, 0.063, 0.153, 0.086] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4274 | {
"bytes": "",
"path": "./images/813e47ec-6304-42c5-82d4-1fc461247965_3cf4529f-653a-47d7-9d84-f577dd79329f.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 set of stainless steel spoons, which are available in stock in San Diego, California.\nPrevious actions:\n[span] -> CLICK\n[path] -> CLICK\n[span] -> CLICK\n[button] Type -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.956, 0.008, 0.988, 0.027] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4275 | {
"bytes": "",
"path": "./images/bdc1f69a-da73-4e51-9dd8-83494d4983c2_7d20bcbf-3186-404e-bea7-f553986347de.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 check-in flight for John Smith having ticket no. 123456780\nPrevious actions:\n[link] Check In -> CLICK\n[textbox] first name maxlimit is 30 -> TYPE: John\n[textbox] last name maxlimit is 30 -> TYPE: Smith\n[select] Confirmation Code -> SELECT: Ticket Number"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.388, 0.367, 0.562, 0.402] in the image\nAnd my action is Action: TYPE\nValue: 123456780"
}
]
|
mind2web_4276 | {
"bytes": "",
"path": "./images/117c1176-b5bd-4b9a-9be2-80a7f390e207_96808158-b0a9-46ad-bddf-d79b9823a094.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 US box office revenue for the highest tomatometer rated movie that the actress playing Sam Carpenter in the most recent Scream movie has been in.\nPrevious actions:\n[textbox] Search -> TYPE: scream\n[p] Neve Campbell, Courteney Cox, David Arquette -> CLICK\n[link] Melissa Barrera -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.312, 0.769, 0.388, 0.783] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4277 | {
"bytes": "",
"path": "./images/39937001-8af2-4727-bb2a-6997981cf50d_23f74267-67c7-467c-a379-2b044cca97f9.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 list of tours available at the Coliseum with free cancellation.\nPrevious actions:\n[span] Top activities -> HOVER\n[span] Colosseum -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.109, 0.279, 0.247, 0.313] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4278 | {
"bytes": "",
"path": "./images/7eff6c15-bab6-4ce4-abb8-72619f593ea1_d0e650ae-54ec-4146-9ae4-b3380b3d6c02.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 my bus with service number SE4.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.425, 0.016, 0.542, 0.075] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4279 | {
"bytes": "",
"path": "./images/cfaa49bd-7943-4da8-ae5f-bb3a15dfaa05_ef74239b-9f8a-4f92-aeba-6ba4ef836c53.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 showtimes for John Wick 4 at a theater in Wichita, Kansas 67226\nPrevious actions:\n[link] Visit the Our Theatres page -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.285, 0.096, 0.488, 0.113] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4280 | {
"bytes": "",
"path": "./images/91f56f3b-e3de-4d57-95df-f976a11c64f7_5a217967-5bc9-47a5-8827-7b36d5e4c9ab.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 veterinarian emergency service for dogs in Hawaii with a BBB rating of A+\nPrevious actions:\n[link] Veterinarians -> CLICK\n[input] -> TYPE: hawaii"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.494, 0.048, 0.788, 0.067] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4281 | {
"bytes": "",
"path": "./images/33064851-00d9-46c8-b0b7-6b5048005c51_fe6c0a7d-c18c-4084-b223-e178afccd592.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 registry in the name of Sheldon Cooper in Arizona and sort by latest to soonest.\nPrevious actions:\n[link] Registry -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.365, 0.183, 0.635, 0.205] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4282 | {
"bytes": "",
"path": "./images/d63b1715-688c-4be2-b196-dde9659bc59d_d816bb8a-ffc1-44f5-b1d4-87e9d0c46851.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: From Birmingham (BHX) to Paris search for packages with casinos, restaurant, fitness and a free internet from April 7th to 11th.\nPrevious actions:\n[textbox] Enter destination or airport -> TYPE: Paris\n[span] City -> CLICK\n[generic] Tuesday April 4th -> CLICK\n[div] 7 -> CLICK\n[button] Tuesday April 11, 2023 -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.945, 0.151, 0.964, 0.167] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4283 | {
"bytes": "",
"path": "./images/d9ab19b6-fecb-4545-ab5d-fabc94c27ff6_d9c94040-4de0-473a-a1c5-6a909a5c5319.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: Hire a premium luxury car closest to North Las Vegas on April 29 at 6 pm and drop it off at the same location and the same day at 11 pm, supplier should be Avis if available.\nPrevious actions:\n[div] Premium -> CLICK\n[label] Distance -> CLICK\n[svg] -> CLICK\n[span] -> CLICK\n[div] View deal -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.481, 0.599, 0.632, 0.677] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4284 | {
"bytes": "",
"path": "./images/5e47dc3e-2a4a-4273-871d-dfdb33b091d5_aff3dec2-7e47-483f-b156-9ff640444b30.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: Filter women's sports bras that are purple with high support that are small size.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.391, 0.028, 0.45, 0.071] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4285 | {
"bytes": "",
"path": "./images/4b99412b-6be2-4274-8843-4fc97f0c8247_7030a4e7-b607-4f7e-92e4-8ca04044bd8b.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 the bus with service number 10000001\nPrevious actions:\n[button] Check my bus -> CLICK\n[link] Track my bus -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.133, 0.17, 0.25, 0.198] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4286 | {
"bytes": "",
"path": "./images/cc174cb2-520d-49c3-93da-f93a1c485c03_48077a71-0bd3-484d-8f19-596861e7e8fb.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: Calculate the fare options to go from the south station to the north station\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.375, 0.007, 0.441, 0.022] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4287 | {
"bytes": "",
"path": "./images/ae969e05-d10e-4255-99f7-c27e071fad69_1f17b922-6a57-438e-84cd-bb7a5d08ddcc.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 standings for the English Premier League.\nPrevious actions:\n[div] … -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.722, 0.093, 0.861, 0.116] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4288 | {
"bytes": "",
"path": "./images/fb73611b-dc68-4a75-bf5b-7e151dc151af_015ff302-508f-4b98-934e-31687f84b870.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 tickets for the Buckeyes football game on April 15th for a group of 5 people.\nPrevious actions:\n[link] BUY TICKETS -> CLICK\n[span] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.916, 0.209, 0.926, 0.218] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4289 | {
"bytes": "",
"path": "./images/fa2828c5-44b3-446e-ae42-a26438ed8343_d7ddf3e3-19d0-496a-b683-73230cc1be3a.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 upcoming departures for the oak grove station going southbound direction\nPrevious actions:\n[combobox] Search MBTA.com -> TYPE: oak grove station\n[button] search -> CLICK\n[link] T orange line bus commuter rail Zone 1A Oak Grove -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.134, 0.136, 0.543, 0.16] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4290 | {
"bytes": "",
"path": "./images/fb73611b-dc68-4a75-bf5b-7e151dc151af_f20c0850-fa76-4979-b946-e7e48831e68a.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 tickets for the Buckeyes football game on April 15th for a group of 5 people.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.766, 0.533, 0.857, 0.554] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4291 | {
"bytes": "",
"path": "./images/2eaf60d5-d2af-4f50-a3ad-5cc9132a770a_4b61c893-4f21-4ecb-8f84-7ce763a40e70.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 the cheapest used women's running shoes available in a size 5\nPrevious actions:\n[radio] GRADE_A -> CLICK\n[button] Add To Cart -> CLICK\n[link] Confirm Membership to Checkout -> CLICK\n[input] -> TYPE: Joe\n[input] -> TYPE: Bloggs"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.055, 0.344, 0.38, 0.375] in the image\nAnd my action is Action: TYPE\nValue: 123456789"
}
]
|
mind2web_4292 | {
"bytes": "",
"path": "./images/86ea50f5-1310-456e-97bf-799d8eb1896b_18dba795-9a54-4dfb-bb8d-b3b849528278.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 NFL Passing yards players stats.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.561, 0.113, 0.621, 0.136] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4293 | {
"bytes": "",
"path": "./images/40fbda9d-22c5-4aab-9798-3db50d981c5c_a651f53a-5897-49f2-b132-6e19082d77c0.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 page to answer a question in the home improvement section.\nPrevious actions:\nNone"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.109, 0.0, 0.288, 0.027] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4294 | {
"bytes": "",
"path": "./images/b5de73d0-820d-45bf-8989-1743a0d9b072_75d85232-55ad-4c33-8fa6-f604a65b9a08.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 closest parking spot to the Orlando Magic at Brooklyn Nets event, happening in Barclays Center, to enter after 3 pm and exit after 5 pm\nPrevious actions:\n[textbox] Search for parking -> TYPE: barclays center\n[li] Barclays Center, Atlantic Avenue, Brooklyn, NY, US... -> CLICK\n[p] Orlando Magic at Brooklyn Nets -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.28, 0.389, 0.397, 0.402] in the image\nAnd my action is Action: SELECT\nValue: Sort by Distance"
}
]
|
mind2web_4295 | {
"bytes": "",
"path": "./images/1a35becb-e07b-4235-8cd3-fc2a29f8dd6f_dc3b0597-0b0b-44a3-922a-df69bcb0df24.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 the most most popular of all time tab to a playlist\nPrevious actions:\n[link] Tabs -> CLICK\n[link] Tab -> CLICK\n[svg] -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.825, 0.142, 0.97, 0.157] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4296 | {
"bytes": "",
"path": "./images/e3486ac5-6d1e-476f-b389-2e6df37f94bd_21008ae4-2f47-4263-93cf-a947f4c43b2e.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] Enter a destination or property -> TYPE: bali\n[generic] Indonesia -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.58, 0.292, 0.584, 0.3] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4297 | {
"bytes": "",
"path": "./images/b3fbf029-aa63-4dd1-879f-47d8abbae4d4_32691a48-f07e-4724-8c49-ba80367012ce.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 attorney for divorce in Union City, NJ.\nPrevious actions:\n[link] Attorneys -> CLICK\n[input] -> TYPE: Union City Nj\n[link] Union City, NJ -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.789, 0.009, 0.867, 0.04] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4298 | {
"bytes": "",
"path": "./images/ccb7c231-8655-4613-a28f-beb8074c523e_96d386cb-2247-46a8-8589-52d65dd3f735.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 Under Armour Return Policy for Men's UA Football All Over Print Metal Logo Short Sleeve\nPrevious actions:\n[menuitem] Men -> CLICK\n[link] Shirts & Tops -> CLICK\n[link] Graphic T-shirts -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.044, 0.275, 0.233, 0.299] in the image\nAnd my action is Action: CLICK"
}
]
|
mind2web_4299 | {
"bytes": "",
"path": "./images/fd2e9403-3201-4bb7-a19d-f475960cf5be_1efe7992-b578-46ea-bbc0-6720f221b9fe.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 Thai restaurants that offer delivery and have vegan options available.\nPrevious actions:\n[textbox] Find -> TYPE: thai restaurants\n[span] Thai Restaurants -> CLICK"
},
{
"from": "gpt",
"value": "For my next step, the target element of my action is bounded by the box [0.227, 0.102, 0.313, 0.114] 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.