Triple

T14549470
Position Surface form Disambiguated ID Type / Status
Subject Grilly E341375 entity
Predicate hasBorder P224 FINISHED
Object Sauverny E341374 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: Sauverny | Statement: [Grilly, hasBorder, Sauverny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sauverny
Context triple: [Grilly, hasBorder, Sauverny]
  • A. Sauverny chosen
    Sauverny is a small commune in eastern France’s Ain department, near the Swiss border and the Geneva metropolitan area.
  • B. Souvigny
    Souvigny is a historic town in central France known for its important Cluniac priory and medieval religious heritage.
  • C. Yerville
    Yerville is a small commune in the Seine-Maritime department of the Normandy region in northern France.
  • D. Chauvigny
    Chauvigny is a historic town in western France known for its medieval fortifications and picturesque setting in the Vienne department of the Nouvelle-Aquitaine region.
  • E. Vallentigny
    Vallentigny is a small French commune located in the Aube department in the Grand Est region of north-central France.
  • 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_69d822db9c8481908213ceb39585f792 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb2ed2b4c8190945bd26531c71f1f completed April 14, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a6344b08190a3c1124c6dd7da96 completed May 8, 2026, 5:53 a.m.
Created at: April 10, 2026, 1:23 a.m.