Triple

T6706706
Position Surface form Disambiguated ID Type / Status
Subject Consulate E153024 entity
Predicate keyFigure P256 FINISHED
Object Pierre-Roger Ducos E27047 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: Pierre-Roger Ducos | Statement: [Consulate, keyFigure, Pierre-Roger Ducos]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pierre-Roger Ducos
Context triple: [Consulate, keyFigure, Pierre-Roger Ducos]
  • A. Pierre-Roger Ducos chosen
    Pierre-Roger Ducos was a French revolutionary politician who served as one of the three provisional consuls alongside Napoleon Bonaparte following the Coup of 18 Brumaire.
  • B. Jacques Dixmier
    Jacques Dixmier is a French mathematician renowned for his foundational work in operator algebras and representation theory.
  • C. Guillaume d’Ornano
    Guillaume d’Ornano was a French businessman and entrepreneur best known for co-founding the luxury cosmetics and perfume house Lancôme in the 1930s.
  • D. Pierre Bérégovoy
    Pierre Bérégovoy was a French Socialist politician who served as Prime Minister of France in the early 1990s under President François Mitterrand.
  • E. François Séverin Marceau-Desgraviers
    François Séverin Marceau-Desgraviers was a French general of the Revolutionary Wars, celebrated for his military talent and heroic death at a young age.
  • 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_69c68808d8d8819087369015270788fe completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d1033bb881908c3360b715bf13cf completed March 27, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7423de3808190866d0ebc3bfc7530 completed March 28, 2026, 2:51 a.m.
Created at: March 27, 2026, 2:06 p.m.