Triple

T2509723
Position Surface form Disambiguated ID Type / Status
Subject historical province of Champagne E52672 entity
Predicate capital P234 FINISHED
Object Troyes E73536 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: Troyes | Statement: [historical province of Champagne, capital, Troyes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Troyes
Context triple: [historical province of Champagne, capital, Troyes]
  • A. Troyes chosen
    Troyes is a historic city in northeastern France, known for its well-preserved medieval old town, half-timbered houses, and Gothic churches.
  • B. Reims
    Reims is a historic city in northeastern France known for its Gothic cathedral, role in French coronations, and significance during both World Wars.
  • C. Meaux
    Meaux is a historic commune in the Île-de-France region of north-central France, known for its cathedral, World War I heritage, and production of Brie de Meaux cheese.
  • D. Amiens
    Amiens is a historic city in northern France, known for its Gothic cathedral and role as the site of the 1802 Treaty of Amiens.
  • E. Bourges
    Bourges is a historic city in central France known for its well-preserved medieval architecture and its UNESCO-listed Gothic cathedral, Saint-Étienne.
  • 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_69ab4958e76481908a235377dd921c9e completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd1ed94a08190a172a426c2123f36 completed March 7, 2026, 7:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69b4e4c13494819095821f44916329c9 completed March 14, 2026, 4:32 a.m.
Created at: March 6, 2026, 9:46 p.m.