Triple

T7778430
Position Surface form Disambiguated ID Type / Status
Subject Gallo-Roman walls of Le Mans E221451 entity
Predicate surrounds P7850 FINISHED
Object old town of Le Mans E43233 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: old town of Le Mans | Statement: [Gallo-Roman walls of Le Mans, surrounds, old town of Le Mans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: old town of Le Mans
Context triple: [Gallo-Roman walls of Le Mans, surrounds, old town of Le Mans]
  • A. city of Tours
    The city of Tours is a historic city in central France, known for its medieval old town, role as a gateway to the Loire Valley châteaux, and rich cultural heritage.
  • B. Le Mans chosen
    Le Mans is a historic city in northwestern France best known for its annual 24 Hours of Le Mans endurance sports car race.
  • C. La Flèche
    La Flèche is a historic town in western France known for its royal heritage, educational institutions, and the renowned Zoo de La Flèche.
  • D. Roanne
    Roanne is a commune and industrial town in central France, situated on the Loire River and known historically for its textile industry and river port.
  • E. Saint-Mard
    Saint-Mard is a French commune in the Seine-et-Marne department in the Île-de-France region, northeast of Paris.
  • 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_69ca83ebbef881909ac47f789145fef7 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69caa4d4480481909d3e8a4df1345299 completed March 30, 2026, 4:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69caf59dfe5c8190972eb9db1b3ca043 completed March 30, 2026, 10:13 p.m.
Created at: March 30, 2026, 4:16 p.m.