Triple

T17117631
Position Surface form Disambiguated ID Type / Status
Subject Vienne E415380 entity
Predicate confluenceNear P8203 FINISHED
Object Candes-Saint-Martin E298110 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: Candes-Saint-Martin | Statement: [Vienne, confluenceNear, Candes-Saint-Martin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Candes-Saint-Martin
Context triple: [Vienne, confluenceNear, Candes-Saint-Martin]
  • A. Candes-Saint-Martin chosen
    Candes-Saint-Martin is a picturesque historic village in central France, known for its medieval architecture and scenic location at the confluence of the Vienne and Loire rivers.
  • B. Lasserre
    Lasserre is a small rural commune in southwestern France known for being the later-life home of the influential mathematician Alexander Grothendieck.
  • C. Fresnaye
    Fresnaye is an affluent, predominantly residential suburb of Cape Town, South Africa, situated on the slopes of Lion’s Head with views over the Atlantic Ocean.
  • D. Morieux
    Morieux is a coastal commune in the Côtes-d'Armor department of Brittany in northwestern France, known for its scenic shoreline along the English Channel.
  • E. Courcier
    Courcier was a French publishing house known for issuing important mathematical and scientific works in the early 19th century.
  • 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_69d886d090cc8190a39cb94992586905 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3e8075a6c8190954d36eb94d1028a completed April 18, 2026, 8:22 p.m.
NED1 Entity disambiguation (via context triple) batch_6a013a0b69108190ba3ba6ba7f8d3935 completed May 11, 2026, 2:08 a.m.
Created at: April 10, 2026, 5:35 a.m.