Triple

T16876196
Position Surface form Disambiguated ID Type / Status
Subject L'Ivresse du pouvoir E421304 entity
Predicate screenwriter P2831 FINISHED
Object Odile Barski E1258163 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: Odile Barski | Statement: [L'Ivresse du pouvoir, screenwriter, Odile Barski]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Odile Barski
Context triple: [L'Ivresse du pouvoir, screenwriter, Odile Barski]
  • A. Odile Barski chosen
    Odile Barski is a French screenwriter known for her work on films such as "Violette Nozière."
  • B. Séverine Lerczinska
    Séverine Lerczinska is a French actress best known for her role in the classic 1932 film "Boudu Saved from Drowning."
  • C. Eliette Mouret
    Eliette Mouret is a French former fashion model and artist best known as the wife of renowned Austrian conductor Herbert von Karajan.
  • D. Eliette Mouret
    Eliette Mouret is a relatively obscure individual whose publicly available information is minimal and not widely documented.
  • E. Eugénie Risler
    Eugénie Risler was the wife of prominent French statesman and education reformer Jules Ferry.
  • 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_69d889d470fc8190b4aec199636c0c56 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3b7f646308190b5e277b5f51cd315 completed April 18, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0170dd38708190b17cee0ab6cee6eb completed May 11, 2026, 6:02 a.m.
Created at: April 10, 2026, 5:29 a.m.