Triple

T8855087
Position Surface form Disambiguated ID Type / Status
Subject Léonore Baulac E210736 entity
Predicate givenName P17 FINISHED
Object Léonore E33739 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: Léonore | Statement: [Léonore Baulac, givenName, Léonore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Léonore
Context triple: [Léonore Baulac, givenName, Léonore]
  • A. Leonore chosen
    Leonore is a given name, typically considered a variant of Eleanor, used for girls in various European languages.
  • B. Léonore, ou L’amour conjugal
    Léonore, ou L’amour conjugal is a French Revolutionary-era rescue opera by Jean-Nicolas Bouilly that tells the story of a devoted wife who disguises herself as a man to save her unjustly imprisoned husband.
  • C. Mademoiselle de Lancey
    Mademoiselle de Lancey is a portrait painting by the 19th-century French artist Carolus-Duran, exemplifying his elegant, realist style and refined depiction of high-society sitters.
  • D. Sébastienne
    Sébastienne is a French feminine given name, used here as part of the full name Louise Sébastienne Gély.
  • E. Eugénie
    Eugénie was the Empress of the French as the wife of Napoleon III and a prominent political and cultural figure of the Second French Empire.
  • 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_69ca838a424c8190b1ecac115c2927e7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60c7f51881909c847989f31f203a completed April 1, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfa09e6d388190ba8f5d8516b43bc4 completed April 3, 2026, 11:12 a.m.
Created at: March 30, 2026, 6:49 p.m.