Triple

T18528289
Position Surface form Disambiguated ID Type / Status
Subject Facebook Engineering E452772 entity
Predicate supportsProduct P18380 FINISHED
Object Facebook Gaming NE NERFINISHED

How this triple was built (2 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: Facebook Gaming | Statement: [Facebook Engineering, supportsProduct, Facebook Gaming]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Facebook Gaming
Context triple: [Facebook Engineering, supportsProduct, Facebook Gaming]
  • A. Netflix Games
    Netflix Games is Netflix’s mobile gaming service that offers a curated selection of games included with a Netflix subscription and playable without ads or in-app purchases.
  • B. Facebook Watch
    Facebook Watch is Meta Platforms' video-on-demand and streaming platform for hosting, discovering, and monetizing a wide range of video content on Facebook.
  • C. Facebook Portal
    Facebook Portal is a line of smart video-calling devices developed by Meta (formerly Facebook), designed to facilitate hands-free, AI-enhanced communication in the home.
  • D. Facebook chosen
    Facebook is a major global social networking platform that allows users to connect, share content, and communicate online.
  • E. Twitch
    Twitch is a leading live-streaming platform, best known for video game broadcasting, esports coverage, and interactive content communities.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8d387b5548190aa030dad2cb4947e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e533fad2d081908395914d6a6b4eb1 completed April 19, 2026, 7:58 p.m.
Created at: April 10, 2026, 11:37 a.m.