Triple

T22100489
Position Surface form Disambiguated ID Type / Status
Subject Entre Nous E546156 entity
Predicate producer P490 FINISHED
Object Diane Kurys 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: Diane Kurys | Statement: [Entre Nous, producer, Diane Kurys]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diane Kurys
Context triple: [Entre Nous, producer, Diane Kurys]
  • A. Diane Kurys chosen
    Diane Kurys is a French film director, screenwriter, and former actress known for her semi-autobiographical and female-centered dramas.
  • B. Lisa Roughead
    Lisa Roughead is the wife of former Manchester United and England footballer Michael Carrick and is known for largely maintaining a private life outside the public spotlight.
  • C. Brigitte Millar
    Brigitte Millar is a British actress best known for her roles in major film franchises, including the Harry Potter and James Bond series.
  • D. Diane Curtis
    Diane Curtis is an individual known primarily through her association as a friend of Dan Lewis.
  • E. Renée O'Connor
    Renée O'Connor is an American actress best known for playing Gabrielle, the loyal companion of the title character, in the television series "Xena: Warrior Princess."
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1291501508190ad5689be5abb2ba6 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.