Triple

T20536917
Position Surface form Disambiguated ID Type / Status
Subject Louis-Alexandre Berthier E504223 entity
Predicate familyName P18 FINISHED
Object Berthier E504223 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: Berthier | Statement: [Louis-Alexandre Berthier, familyName, Berthier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berthier
Context triple: [Louis-Alexandre Berthier, familyName, Berthier]
  • A. Berthier chosen
    Berthier is a French surname most famously associated with Louis-Alexandre Berthier, a marshal of France and chief of staff to Napoleon.
  • B. Brière
    Brière is a French-language surname most prominently associated with former NHL player and current hockey executive Daniel Brière.
  • C. Charigot
    Charigot is the surname of Aline Charigot, a French woman best known as the model, companion, and later wife of the painter Pierre-Auguste Renoir.
  • D. Plombières
    Plombières is a municipality in the province of Liège in eastern Belgium, near the German and Dutch borders.
  • E. Bourg-Saint-Pierre
    Bourg-Saint-Pierre is a small Swiss village in the canton of Valais, known as a historic stop on the Great St. Bernard Pass near the Italian border.
  • 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a28f2f1081908f656d790ff182ff completed April 20, 2026, 10:02 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0ae99b7ec48190b3ddfe3bf61ab8fb completed May 18, 2026, 10:27 a.m.
Created at: April 16, 2026, 11:37 a.m.