Triple

T1622754
Position Surface form Disambiguated ID Type / Status
Subject ES Troyes AC E35069 entity
Predicate location P40 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: [ES Troyes AC, location, Troyes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Troyes
Context triple: [ES Troyes AC, location, 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. 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.
  • D. Bourges
    Bourges is a historic city in central France known for its well-preserved medieval architecture and its UNESCO-listed Gothic cathedral, Saint-Étienne.
  • E. Tournus
    Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
  • 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_69a886023194819080a3fccd6e325d0e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a909cf3c7481909ddbe6a6596bb0c8 completed March 5, 2026, 4:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69af9040c20c8190aaae6f22fc893032 completed March 10, 2026, 3:30 a.m.
Created at: March 4, 2026, 7:28 p.m.