Triple

T9844846
Position Surface form Disambiguated ID Type / Status
Subject Yuri Milner E239313 entity
Predicate investedIn P17330 FINISHED
Object Zynga E331665 NE FINISHED

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: Zynga | Statement: [Yuri Milner, investedIn, Zynga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zynga
Context triple: [Yuri Milner, investedIn, Zynga]
  • A. Zynga chosen
    Zynga is a video game developer and publisher best known for its popular social and mobile games such as FarmVille and Words With Friends.
  • B. Skydance Interactive
    Skydance Interactive is a video game development and virtual reality studio known for creating immersive, narrative-driven gaming experiences.
  • C. Gameloft
    Gameloft is a French video game developer and publisher best known for creating and distributing mobile games worldwide.
  • D. Glu Mobile
    Glu Mobile is an American mobile game developer and publisher known for creating popular free-to-play titles, including celebrity-branded games.
  • E. Rovio Entertainment
    Rovio Entertainment is a Finnish video game developer and entertainment company best known for creating the Angry Birds franchise.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca84e3f0c48190ada72a65ebd50efd completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb35dc29c819080203be5b904dc9d completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1d5dda4b0819092703270e87bee5a completed April 5, 2026, 3:24 a.m.
Created at: March 30, 2026, 8:33 p.m.