Triple

T23220694
Position Surface form Disambiguated ID Type / Status
Subject Duke of Nevers E580881 entity
Predicate locatedIn P40 FINISHED
Object Nivernais 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: Nivernais | Statement: [Duke of Nevers, locatedIn, Nivernais]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nivernais
Context triple: [Duke of Nevers, locatedIn, Nivernais]
  • A. Nivernais chosen
    Nivernais is a historic province in central France, centered around the town of Nevers and known for its rural landscapes and traditional agriculture.
  • B. Tournaisis
    Tournaisis is a historical region in present-day Belgium centered around the city of Tournai, known for its medieval political significance and rich cultural heritage.
  • C. Verdunois
    Verdunois is a regional dialect of the Lorrain Romance language traditionally spoken around the area of Verdun in northeastern France.
  • D. Dieuzoise
    Dieuzoise is the French demonym referring to a female inhabitant or native of the town of Dieuze in northeastern France.
  • E. Auregnais
    Auregnais is an extinct Norman dialect once spoken on the Channel Island of Alderney.
  • 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_69e2460389408190be74f41d217799a9 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1916870148190853874e6cf26bbc7 completed April 29, 2026, 5:04 a.m.
Created at: April 17, 2026, 4:08 p.m.