Triple

T10128994
Position Surface form Disambiguated ID Type / Status
Subject County of Valois E226286 entity
Predicate capital P234 FINISHED
Object Crépy-en-Valois E726442 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: Crépy-en-Valois | Statement: [County of Valois, capital, Crépy-en-Valois]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crépy-en-Valois
Context triple: [County of Valois, capital, Crépy-en-Valois]
  • A. Crépy-en-Valois chosen
    Crépy-en-Valois is a commune in the Oise department of northern France, known for its historic medieval center and role as a regional rail terminus.
  • B. Pontoise
    Pontoise is a historic commune in the northwestern suburbs of Paris, France, known for its picturesque setting on the River Oise and its association with Impressionist painters.
  • C. Gravelotte
    Gravelotte is a village in northeastern France best known as the site of a major 1870 Franco-Prussian War battle.
  • D. Beauvechain
    Beauvechain is a municipality in Walloon Brabant, Belgium, known for its rural character and the presence of a major Belgian Air Component base.
  • E. Armentières
    Armentières is a commune in northern France near the Belgian border, historically known for its textile industry and World War I significance.
  • 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_69ca843057b48190a86730167f5d6b98 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd333186c819088bbf617967f24fa completed April 2, 2026, 2:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cc72848481909dcbfc9fe3f6d379 completed April 5, 2026, 8:56 p.m.
Created at: March 30, 2026, 9:05 p.m.