Triple

T22233661
Position Surface form Disambiguated ID Type / Status
Subject Chocolat E549530 entity
Predicate stars P1956 FINISHED
Object Clotilde Hesme 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: Clotilde Hesme | Statement: [Chocolat, stars, Clotilde Hesme]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Clotilde Hesme
Context triple: [Chocolat, stars, Clotilde Hesme]
  • A. Clotilde Hesme chosen
    Clotilde Hesme is a French actress known for her work in film, television, and theater, including a prominent role in the series "Lupin."
  • B. Clotilde Baudon
    Clotilde Baudon is a French actress best known for her role in the 1985 coming-of-age film "L'Effrontée."
  • C. Renée de Monpezat
    Renée de Monpezat was a French noblewoman best known as the mother of Prince Henrik, the late Prince Consort of Denmark.
  • D. Clémence Desmarets
    Clémence Desmarets is a central fictional character in Honoré de Balzac’s novel "Ferragus," known for her beauty, virtue, and tragic entanglement in a web of Parisian intrigue and secrecy.
  • E. Jacqueline de Sibour
    Jacqueline de Sibour was an American socialite and actress best known for her marriage to actor and comedian Orson Bean.
  • 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12bf61504819093e70bee4c575d1c completed April 28, 2026, 9:51 p.m.
Created at: April 16, 2026, 8:38 p.m.