Triple

T21129933
Position Surface form Disambiguated ID Type / Status
Subject Adam Lesage E520658 entity
Predicate associatedWith P37 FINISHED
Object La Voisin 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: La Voisin | Statement: [Adam Lesage, associatedWith, La Voisin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: La Voisin
Context triple: [Adam Lesage, associatedWith, La Voisin]
  • A. La Voisin chosen
    La Voisin was a notorious 17th-century French fortune-teller and alleged sorceress central to the Affair of the Poisons scandal at the court of Louis XIV.
  • B. Bachet Noir
    Bachet Noir is a rare, old French wine grape variety historically used in the Champagne region and known primarily as a parent of the modern grape variety Gamay.
  • C. La Duchère
    La Duchère is a residential district in Lyon known for its large post-war housing estates, urban renewal projects, and hilltop views over the city.
  • D. Madame La Motte
    Madame La Motte is a central character in Ann Radcliffe’s Gothic novel "The Romance of the Forest," depicted as the anxious, morally conflicted wife of an impoverished fugitive.
  • E. Le Prestre
    Le Prestre is the noble Breton family name of Sébastien Le Prestre de Vauban, the famed 17th-century French military engineer and marshal.
  • 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_69e0b50b53048190ae34e8abbe3c5ada completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e723556ec08190a2ade96c76f9cec7 completed April 21, 2026, 7:12 a.m.
Created at: April 16, 2026, 2:56 p.m.