Triple

T17800361
Position Surface form Disambiguated ID Type / Status
Subject Maurice Sarrail E444406 entity
Predicate familyName P18 FINISHED
Object Sarrail 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: Sarrail | Statement: [Maurice Sarrail, familyName, Sarrail]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarrail
Context triple: [Maurice Sarrail, familyName, Sarrail]
  • A. Corcelette
    Corcelette is a renowned vineyard site in the Morgon appellation of Beaujolais, known for producing structured, age-worthy Gamay wines.
  • B. Charroux
    Charroux is a historic commune in western France known for its medieval heritage and the remains of its once-prominent Benedictine abbey.
  • C. Beauharnois
    Beauharnois is a town in southwestern Quebec, Canada, known for its location along the Saint Lawrence River and the large Beauharnois hydroelectric generating station.
  • D. Souain chosen
    Souain is a commune in the Marne department of northeastern France, known for its World War I battlefields and memorials.
  • E. Vaugier
    Vaugier is the surname of Emmanuelle Vaugier, a Canadian actress and model known for roles in television series such as "Two and a Half Men" and "Smallville."
  • 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e487ff42108190b82ceb4466aa2dff completed April 19, 2026, 7:45 a.m.
Created at: April 10, 2026, 10:13 a.m.