Triple

T8619894
Position Surface form Disambiguated ID Type / Status
Subject Star Wars: TIE Fighter E204136 entity
Predicate developer P73 FINISHED
Object Totally Games E202721 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: Totally Games | Statement: [Star Wars: TIE Fighter, developer, Totally Games]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Totally Games
Context triple: [Star Wars: TIE Fighter, developer, Totally Games]
  • A. Totally Games chosen
    Totally Games was a video game development studio best known for creating the Star Wars: X-Wing and TIE Fighter space combat simulators.
  • B. Alva Games
    Alva Games is an annual gaming event held in Alva that features video game competitions, community activities, and entertainment for gaming enthusiasts.
  • C. The Gamester
    The Gamester is a Caroline-era tragicomedy play by English dramatist James Shirley, centered on themes of gambling, honor, and social intrigue.
  • D. The Happy Games
    The Happy Games was the official motto of the 1972 Summer Olympics in Munich, reflecting the organizers’ aim to present a cheerful, peaceful image of Germany.
  • E. Toys for Bob
    Toys for Bob is an American video game developer best known for creating the Skylanders series and working on remakes like the Spyro Reignited Trilogy.
  • 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_69ca832ceab8819096e4a9f546695079 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc471458f48190a6d8858f8074727d completed March 31, 2026, 10:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebbd49cc8819093555edf5ff0acaa completed April 2, 2026, 6:56 p.m.
Created at: March 30, 2026, 6:26 p.m.