Triple

T21891176
Position Surface form Disambiguated ID Type / Status
Subject Marshal Villars E540550 entity
Predicate familyName P18 FINISHED
Object de Villars 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: de Villars | Statement: [Marshal Villars, familyName, de Villars]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: de Villars
Context triple: [Marshal Villars, familyName, de Villars]
  • A. de Villars chosen
    de Villars is a French noble family name historically associated with prominent military and aristocratic figures.
  • B. Pierre de Villars
    Pierre de Villars was a 17th-century French diplomat and nobleman who notably served as ambassador to Spain under King Louis XIV.
  • C. de Montferrand
    de Montferrand is the French noble family name borne by architect Auguste de Montferrand, renowned for designing Saint Isaac's Cathedral in Saint Petersburg.
  • D. Gagnière
    Gagnière is a French surname, likely of regional origin, associated with individuals such as Mahoudeau.
  • E. d’Esmier d’Olbreuse
    d’Esmier d’Olbreuse is a French noble family name historically associated with Eleonore d’Esmier d’Olbreuse, the morganatic wife of George William, Duke of Brunswick-Lüneburg, and ancestress of several European royal lines.
  • 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_69e0c47a95908190ae3e19b716accb3d completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f11fc3727c8190b4d5d5a44aa2e55e completed April 28, 2026, 8:59 p.m.
Created at: April 16, 2026, 7:06 p.m.