Viewing enriched Twitter post
Instead spreadsheets for data review, I'm using a little custom annotation app build with @AirWebFramework. Before I used to use django for building little eval apps mostly because of the forms api, orm, and admin, but now I've moved to Air since it's light weight and easy. https://t.co/T7OKpRQWCE
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1957172624129413542/media_0.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1957172624129413542/media_0.jpg?",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2025-08-27T13:15:49.617399",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "1957172624129413542",
"url": "https://x.com/Nate_somewhere/status/1957172624129413542",
"twitterUrl": "https://twitter.com/Nate_somewhere/status/1957172624129413542",
"text": "Instead spreadsheets for data review, I'm using a little custom annotation app build with @AirWebFramework.\n\nBefore I used to use django for building little eval apps mostly because of the forms api, orm, and admin, but now I've moved to Air since it's light weight and easy. https://t.co/T7OKpRQWCE",
"source": "Twitter for iPhone",
"retweetCount": 6,
"replyCount": 1,
"likeCount": 12,
"quoteCount": 0,
"viewCount": 4192,
"createdAt": "Sun Aug 17 20:08:10 +0000 2025",
"lang": "en",
"bookmarkCount": 5,
"isReply": false,
"inReplyToId": null,
"conversationId": "1957172624129413542",
"displayTextRange": [
0,
275
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "Nate_somewhere",
"url": "https://x.com/Nate_somewhere",
"twitterUrl": "https://twitter.com/Nate_somewhere",
"id": "3374261",
"name": "Nathan Danielsen",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1354285967893360645/SfQ32DG5_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/3374261/1556974558",
"description": "",
"location": "Pasadena, CA",
"followers": 523,
"following": 596,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Tue Apr 03 23:53:06 +0000 2007",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 6226,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 121,
"statusesCount": 777,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1480327578820878337"
],
"profile_bio": {
"description": "Living the dream. @pydatala, @peacecorps, @scikit_yb also slow triathlete but getting faster. Deep into automotive data and AI @carvana",
"entities": {
"description": {
"user_mentions": [
{
"id_str": "0",
"indices": [
18,
27
],
"name": "",
"screen_name": "pydatala"
},
{
"id_str": "0",
"indices": [
29,
40
],
"name": "",
"screen_name": "peacecorps"
},
{
"id_str": "0",
"indices": [
42,
52
],
"name": "",
"screen_name": "scikit_yb"
},
{
"id_str": "0",
"indices": [
129,
137
],
"name": "",
"screen_name": "carvana"
}
]
},
"url": {
"urls": [
{
"display_url": "nathandanielsen.com",
"expanded_url": "https://www.nathandanielsen.com/",
"indices": [
0,
23
],
"url": "https://t.co/gSqCzvHgXc"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/T7OKpRQWCE",
"expanded_url": "https://twitter.com/Nate_somewhere/status/1957172624129413542/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {},
"orig": {}
},
"id_str": "1957171799273377792",
"indices": [
276,
299
],
"media_key": "3_1957171799273377792",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARspRWHEGhAACgACGylGIdFaUaYAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABGylFYcQaEAAKAAIbKUYh0VpRpgAA",
"media_key": "3_1957171799273377792"
}
},
"media_url_https": "https://pbs.twimg.com/media/GylFYcQaEAAKHfh.jpg",
"original_info": {
"focus_rects": [
{
"h": 865,
"w": 1544,
"x": 0,
"y": 0
},
{
"h": 1228,
"w": 1228,
"x": 316,
"y": 0
},
{
"h": 1228,
"w": 1077,
"x": 425,
"y": 0
},
{
"h": 1228,
"w": 614,
"x": 656,
"y": 0
},
{
"h": 1228,
"w": 1544,
"x": 0,
"y": 0
}
],
"height": 1228,
"width": 1544
},
"sizes": {
"large": {
"h": 1228,
"w": 1544
}
},
"type": "photo",
"url": "https://t.co/T7OKpRQWCE"
}
]
},
"card": null,
"place": {},
"entities": {
"user_mentions": [
{
"id_str": "1954659144277147648",
"indices": [
90,
106
],
"name": "Air Web Framework",
"screen_name": "AirWebFramework"
}
]
},
"quoted_tweet": {
"type": "tweet",
"id": "1957156945124790550",
"url": "https://x.com/Nate_somewhere/status/1957156945124790550",
"twitterUrl": "https://twitter.com/Nate_somewhere/status/1957156945124790550",
"text": "Looking at my data from a another perspective now. I'm looking at code-based and llm judge results for extraction from a PDF. \n\nI'm trying to determine a clear-cut threshold for flagging these llm outputs for human review.",
"source": "Twitter for iPhone",
"retweetCount": 1,
"replyCount": 1,
"likeCount": 5,
"quoteCount": 1,
"viewCount": 6840,
"createdAt": "Sun Aug 17 19:05:52 +0000 2025",
"lang": "en",
"bookmarkCount": 2,
"isReply": false,
"inReplyToId": null,
"conversationId": "1957156945124790550",
"displayTextRange": [
0,
222
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "Nate_somewhere",
"url": "https://x.com/Nate_somewhere",
"twitterUrl": "https://twitter.com/Nate_somewhere",
"id": "3374261",
"name": "Nathan Danielsen",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1354285967893360645/SfQ32DG5_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/3374261/1556974558",
"description": "",
"location": "Pasadena, CA",
"followers": 523,
"following": 596,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Tue Apr 03 23:53:06 +0000 2007",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 6226,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 121,
"statusesCount": 777,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1480327578820878337"
],
"profile_bio": {
"description": "Living the dream. @pydatala, @peacecorps, @scikit_yb also slow triathlete but getting faster. Deep into automotive data and AI @carvana",
"entities": {
"description": {
"user_mentions": [
{
"id_str": "0",
"indices": [
18,
27
],
"name": "",
"screen_name": "pydatala"
},
{
"id_str": "0",
"indices": [
29,
40
],
"name": "",
"screen_name": "peacecorps"
},
{
"id_str": "0",
"indices": [
42,
52
],
"name": "",
"screen_name": "scikit_yb"
},
{
"id_str": "0",
"indices": [
129,
137
],
"name": "",
"screen_name": "carvana"
}
]
},
"url": {
"urls": [
{
"display_url": "nathandanielsen.com",
"expanded_url": "https://www.nathandanielsen.com/",
"indices": [
0,
23
],
"url": "https://t.co/gSqCzvHgXc"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}