Triple

T14520936
Position Surface form Disambiguated ID Type / Status
Subject Poison (film) E340648 entity
Predicate productionCompany P490 FINISHED
Object Apparatus Productions E126638 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: Apparatus Productions | Statement: [Poison (film), productionCompany, Apparatus Productions]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Apparatus Productions
Context triple: [Poison (film), productionCompany, Apparatus Productions]
  • A. Apparatus Productions chosen
    Apparatus Productions is a film production company known for working on period dramas such as "The Young Victoria."
  • B. Quad Productions
    Quad Productions is a French film and advertising production company known for creating high-profile commercials and feature films.
  • C. Forge Productions
    Forge Productions is a film production company best known for its involvement in the big-budget 1995 pirate adventure movie "Cutthroat Island."
  • D. Tailwind Productions
    Tailwind Productions is a film and television production company known for developing and producing screen content, including the movie "Touch."
  • E. Central Productions
    Central Productions is the television production company best known for producing the satirical news program "The Daily Show."
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de9a72cff08190878b4bed9b0b5eb5 completed April 14, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a4b71688190ae9ebccdc81d09f8 completed May 8, 2026, 5:53 a.m.
Created at: April 10, 2026, 1:22 a.m.