Triple

T17550723
Position Surface form Disambiguated ID Type / Status
Subject Canal de Roanne à Digoin E427453 entity
Predicate connectsCity P4245 FINISHED
Object Digoin 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: Digoin | Statement: [Canal de Roanne à Digoin, connectsCity, Digoin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Digoin
Context triple: [Canal de Roanne à Digoin, connectsCity, Digoin]
  • A. Digoin chosen
    Digoin is a commune in eastern France known for its location at the junction of several canals and the Loire River in the Saône-et-Loire department.
  • B. Davigo
    Davigo is an Italian surname most notably associated with Piercamillo Davigo, a prominent magistrate and former member of Italy’s anti-corruption "Mani Pulite" (Clean Hands) investigation.
  • C. Drangan
    Drangan is a small rural village in County Tipperary, Ireland, known for its traditional Irish countryside setting and local community life.
  • D. Dagonet
    Dagonet is the loyal and self-sacrificing knight of the Round Table in the 2004 film "King Arthur," portrayed as a fierce warrior and close companion to Arthur and his fellow knights.
  • E. Longido
    Longido is a town in northern Tanzania that serves as a local center near Mount Longido and the Kenyan border within the Arusha Region.
  • 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_69d889df6dc081908f67dbadc03c07ee completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e454656dc08190bba85b93bd07b0a2 completed April 19, 2026, 4:04 a.m.
Created at: April 10, 2026, 5:50 a.m.