Triple

T23476149
Position Surface form Disambiguated ID Type / Status
Subject Louis Jules Trochu E570268 entity
Predicate describedBySource P519 FINISHED
Object Larousse 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: Larousse | Statement: [Louis Jules Trochu, describedBySource, Larousse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larousse
Context triple: [Louis Jules Trochu, describedBySource, Larousse]
  • A. Le Petit Larousse
    Le Petit Larousse is a famous French single-volume encyclopedic dictionary widely used for its comprehensive coverage of the French language and general knowledge.
  • B. Larousse Encyclopedia
    The Larousse Encyclopedia is a comprehensive French reference work covering a wide range of subjects, published by the renowned Larousse publishing house.
  • C. Le Petit Robert
    Le Petit Robert is a widely used monolingual French dictionary renowned for its comprehensive coverage of contemporary French vocabulary and usage.
  • D. Desclée
    Desclée is a Catholic publishing house historically known for producing liturgical and Gregorian chant books, including the Liber Usualis.
  • E. Éditions Larousse chosen
    Éditions Larousse is a renowned French publishing house best known for its dictionaries, encyclopedias, and reference works in the French language.
  • 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_69e245af8a88819084f2704f6d265a92 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a74cf57081909d2b90a806d68c08 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:01 p.m.