Triple

T13414297
Position Surface form Disambiguated ID Type / Status
Subject Duchy of Berry E313168 entity
Predicate borderedBy P224 FINISHED
Object Nivernais E150661 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: Nivernais | Statement: [Duchy of Berry, borderedBy, Nivernais]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nivernais
Context triple: [Duchy of Berry, borderedBy, 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. Auregnais
    Auregnais is an extinct Norman dialect once spoken on the Channel Island of Alderney.
  • D. Vendômois
    Vendômois is the French demonym referring to inhabitants or natives of the town of Vendôme in central France.
  • E. Barrois
    Barrois is a historical region in northeastern France that formed the core territory of the medieval County of Bar.
  • 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_69d806ad0c44819088833ae1ec9e9690 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaeb556948190af008c88e5bbf051 completed April 12, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7308095548190afb659b84f2775f2 completed May 3, 2026, 11:24 a.m.
Created at: April 9, 2026, 9:39 p.m.