Triple

T10212582
Position Surface form Disambiguated ID Type / Status
Subject 8th Academy Awards E242366 entity
Predicate bestActorWinnerWork P8115 FINISHED
Object The Informer E261639 NE FINISHED

How this triple was built (3 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: The Informer | Statement: [8th Academy Awards, bestActorWinnerWork, The Informer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Informer
Context triple: [8th Academy Awards, bestActorWinnerWork, The Informer]
  • A. The Informer chosen
    The Informer is a 1935 American drama film directed by John Ford, renowned for its expressionistic style and Ford’s Oscar-winning direction.
  • B. The Valachi Papers
    The Valachi Papers is a 1972 crime film dramatizing the real-life testimony of Mafia informant Joe Valachi and exposing the inner workings of the American Cosa Nostra.
  • C. L’Homme qui assassina
    L’Homme qui assassina is a French film best known for featuring actor Pierre Fresnay in a prominent role.
  • D. The Manchurian Candidate
    The Manchurian Candidate is a 1962 political thriller film about brainwashing and Cold War conspiracy, widely regarded as a classic of American cinema.
  • E. The Boy Who Knew Too Much
    The Boy Who Knew Too Much is the second studio album by British singer-songwriter Mika, known for its theatrical pop sound and catchy, upbeat tracks.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: bestActorWinnerWork
Context triple: [8th Academy Awards, bestActorWinnerWork, The Informer]
  • A. bestActorWinner chosen
    Indicates that the subject is the recipient of a "Best Actor" award for a particular performance or event.
  • B. bestActorMotionPictureMusicalOrComedyWork
    Indicates that an entity received the Best Actor in a Motion Picture – Musical or Comedy award for a specific work.
  • C. bestActorMotionPictureDramaWork
    Indicates that a person received the award for best actor in a motion picture drama for a specific work.
  • D. bestPictureWinner
    Indicates that the subject is the film that won the Best Picture award in a given context or year.
  • E. bestScoringOfADramaticOrComedyPictureWinner
    Indicates that the subject is the winner for best scoring of a dramatic or comedy motion picture.
  • F. None of above.

Provenance (4 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_69d381ae26c48190985abd0e25ee5d04 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d3aa23bce881909b5deac612ec22cb completed April 6, 2026, 12:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d6f6f4d0cc8190ae41277b15b3012d completed April 9, 2026, 12:46 a.m.
PD Predicate disambiguation batch_69d39559e5ac8190b88eca75956b7e6a completed April 6, 2026, 11:13 a.m.
Created at: April 6, 2026, 11:03 a.m.