Triple

T10855899
Position Surface form Disambiguated ID Type / Status
Subject Catherine Deneuve E256268 entity
Predicate notableWork P4 FINISHED
Object Tristana E223574 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: Tristana | Statement: [Catherine Deneuve, notableWork, Tristana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tristana
Context triple: [Catherine Deneuve, notableWork, Tristana]
  • A. Tristana chosen
    Tristana is a 1970 Spanish drama film directed by Luis Buñuel, known for its exploration of power, morality, and desire through the story of a young woman and her older guardian.
  • B. Katarina
    Katarina is a feminine given name, commonly used in various European cultures, that is a variant of the name Catherine.
  • C. Leona
    Leona is a feminine given name used in various cultures, often derived from the Latin word for "lion."
  • D. Katarina Taikon
    Katarina Taikon was a prominent Swedish Romani activist and author, best known for her influential autobiographical "Katitzi" book series that highlighted Roma rights and experiences.
  • E. Maria Lilina
    Maria Lilina was a prominent Russian stage actress of the Moscow Art Theatre and the wife and close artistic collaborator of theatre director Konstantin Stanislavski.
  • 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_69d6aa83d1448190a66d93c32394d21f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d75135df24819090ce43afa3ea9b38 completed April 9, 2026, 7:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb197808c8190b1c80aeb2144a909 completed April 14, 2026, 9:28 p.m.
Created at: April 8, 2026, 9:20 p.m.