Triple

T20602681
Position Surface form Disambiguated ID Type / Status
Subject WB Games San Francisco E506221 entity
Predicate brand P1500 FINISHED
Object WB Games 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: WB Games | Statement: [WB Games San Francisco, brand, WB Games]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WB Games
Context triple: [WB Games San Francisco, brand, WB Games]
  • A. WB Games San Francisco chosen
    WB Games San Francisco is a video game development studio under Warner Bros. Games known for creating mobile and online titles based on popular Warner Bros. entertainment franchises.
  • B. WB Games Montréal
    WB Games Montréal is a Canadian video game development studio best known for creating titles in the Batman: Arkham series and other DC Comics–based games.
  • C. Activision Blizzard
    Activision Blizzard is a major American video game holding company known for franchises such as Call of Duty, World of Warcraft, and Overwatch.
  • D. SJ Games
    SJ Games is a tabletop game publisher best known for producing titles like GURPS, Munchkin, and various strategy and role-playing games.
  • E. Locomotive Games
    Locomotive Games was a video game development studio known for working on licensed titles, including adaptations of popular film franchises.
  • 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_69e0b4ba6ae88190af871e1f9522c704 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aa20f5c881909265ce7d96efc487 completed April 20, 2026, 10:35 p.m.
Created at: April 16, 2026, 11:41 a.m.