Triple

T5422907
Position Surface form Disambiguated ID Type / Status
Subject Picard language E121293 entity
Predicate hasDialect P4251 FINISHED
Object Vermandois E474072 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: Vermandois | Statement: [Picard language, hasDialect, Vermandois]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vermandois
Context triple: [Picard language, hasDialect, Vermandois]
  • A. Picardy
    Picardy is a historical region in northern France known for its strategic location, rich medieval heritage, and significant role in European conflicts.
  • B. Vendômois
    Vendômois is the French demonym referring to inhabitants or natives of the town of Vendôme in central France.
  • C. Champagne-Ardenne
    Champagne-Ardenne was a former administrative region in northeastern France, renowned for its Champagne wine production and historic cities such as Reims and Troyes.
  • D. Soissonnais chosen
    Soissonnais is a historical region in northern France centered around the city of Soissons, known for its early medieval significance and role in the Frankish kingdom.
  • E. Upper Lorraine
    Upper Lorraine was a historical duchy in the Holy Roman Empire, centered in what is now northeastern France and parts of neighboring countries, known for its predominantly German-speaking population and strategic position between France and Germany.
  • 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_69bd463b58d88190b258261573de9e91 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd8812f84c819094d8516f69fff83d completed March 20, 2026, 5:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf6c548a40819086910fbc39b21e90 completed March 22, 2026, 4:13 a.m.
Created at: March 20, 2026, 2:06 p.m.