Triple

T20561631
Position Surface form Disambiguated ID Type / Status
Subject Milena Canonero E504854 entity
Predicate collaboratedWith P435 FINISHED
Object Hugh Hudson 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: Hugh Hudson | Statement: [Milena Canonero, collaboratedWith, Hugh Hudson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hugh Hudson
Context triple: [Milena Canonero, collaboratedWith, Hugh Hudson]
  • A. Hugh Hudson chosen
    Hugh Hudson was a British film director best known for his Academy Award–winning 1981 sports drama "Chariots of Fire."
  • B. John Guillermin
    John Guillermin was a British film director known for his work on large-scale adventure and disaster films, including the 1976 remake of King Kong and The Towering Inferno.
  • C. Robert Mulligan
    Robert Mulligan was an American film director best known for his sensitive, character-driven dramas, including the acclaimed adaptation of Harper Lee’s "To Kill a Mockingbird."
  • D. Clive Donner
    Clive Donner was a British film director known for his work in 1960s cinema, including influential comedies and literary adaptations.
  • E. J. Lee Thompson
    J. Lee Thompson was a British film director known for a wide range of popular movies, including war epics, thrillers, and collaborations with major Hollywood stars.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a79ec10481909740eb6a08ae2658 completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.