Triple

T6126948
Position Surface form Disambiguated ID Type / Status
Subject Tulip Fever E136616 entity
Predicate castMember P1668 FINISHED
Object Anjelica Huston E199236 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: Anjelica Huston | Statement: [Tulip Fever, castMember, Anjelica Huston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anjelica Huston
Context triple: [Tulip Fever, castMember, Anjelica Huston]
  • A. Anjelica Huston chosen
    Anjelica Huston is an acclaimed American actress and director known for her distinctive presence and award-winning performances in films such as "Prizzi's Honor" and "The Addams Family."
  • B. Shirley Hayden
    Shirley Hayden is a musician best known as a member of Kid Rock’s backing band, Twisted Brown Trucker.
  • C. Lee Remick
    Lee Remick was an American actress acclaimed for her nuanced performances in film, television, and theater, notably in works like "Anatomy of a Murder" and "Days of Wine and Roses."
  • D. Faye Dunaway
    Faye Dunaway is an acclaimed American actress known for her intense, charismatic performances in classic films such as "Bonnie and Clyde," "Chinatown," and "Network."
  • E. Holly Hunter
    Holly Hunter is an Academy Award–winning American actress known for her intense, nuanced performances in films such as "The Piano," "Broadcast News," and "Raising Arizona."
  • 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_69c008a0a37c81908e5b4f879158afb3 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05c2a13a48190b80e11d58fc87c8a completed March 22, 2026, 9:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c669d473388190a6e998956dd48e7a completed March 27, 2026, 11:28 a.m.
Created at: March 22, 2026, 4:15 p.m.