Triple

T3421083
Position Surface form Disambiguated ID Type / Status
Subject Pixel Launcher E72115 entity
Predicate hasFeature P182 FINISHED
Object Google Discover feed
Google Discover feed is a personalized content stream on Android that surfaces news, articles, and other information based on a user’s interests and activity.
E356367 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Google Discover feed | Statement: [Pixel Launcher, hasFeature, Google Discover feed]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Google Discover feed
Context triple: [Pixel Launcher, hasFeature, Google Discover feed]
  • A. StumbleUpon
    StumbleUpon was a popular discovery and recommendation platform that let users "stumble" through personalized web content based on their interests.
  • B. Google Reader
    Google Reader was a web-based RSS and Atom feed aggregator by Google that allowed users to subscribe to and read syndicated website content until its shutdown in 2013.
  • C. iDiscover
    iDiscover is the online search and discovery platform used to access Cambridge University’s library collections, including books, journals, and electronic resources.
  • D. Google Now on Tap
    Google Now on Tap was an Android feature that provided context-aware search and assistance by analyzing on-screen content and offering relevant information and actions without leaving the current app.
  • E. Google Gemini
    Google Gemini is Google's family of advanced multimodal AI models designed to handle text, code, images, and other data types for a wide range of intelligent applications.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Google Discover feed
Triple: [Pixel Launcher, hasFeature, Google Discover feed]
Generated description
Google Discover feed is a personalized content stream on Android that surfaces news, articles, and other information based on a user’s interests and activity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Google Discover feed
Target entity description: Google Discover feed is a personalized content stream on Android that surfaces news, articles, and other information based on a user’s interests and activity.
  • A. StumbleUpon
    StumbleUpon was a popular discovery and recommendation platform that let users "stumble" through personalized web content based on their interests.
  • B. Google News chosen
    Google News is a news aggregation service by Google that compiles and personalizes headlines and articles from thousands of publishers worldwide.
  • C. Google Reader
    Google Reader was a web-based RSS and Atom feed aggregator by Google that allowed users to subscribe to and read syndicated website content until its shutdown in 2013.
  • D. iDiscover
    iDiscover is the online search and discovery platform used to access Cambridge University’s library collections, including books, journals, and electronic resources.
  • E. Google Now on Tap
    Google Now on Tap was an Android feature that provided context-aware search and assistance by analyzing on-screen content and offering relevant information and actions without leaving the current app.
  • F. None of above.

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ad85ad38e48190b7660c5118a35289 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb950f65481908c4aad15516e7a7c completed March 8, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_69b35472881c8190baf90b91daa924ec completed March 13, 2026, 12:04 a.m.
NEDg Description generation batch_69b35585fbd08190966c1263c165daa9 completed March 13, 2026, 12:08 a.m.
NED2 Entity disambiguation (via description) batch_69b3566da174819086160cd254e0a443 completed March 13, 2026, 12:12 a.m.
Created at: March 8, 2026, 3:15 p.m.