Triple

T14843939
Position Surface form Disambiguated ID Type / Status
Subject Picard E349035 entity
Predicate hasDialect P4251 FINISHED
Object Lillois
Lillois is a regional dialect of the Picard language traditionally spoken in and around the city of Lille in northern France.
 E1123222 NE FINISHED

How this triple was built (4 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: Lillois | Statement: [Picard, hasDialect, Lillois]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lillois
Context triple: [Picard, hasDialect, Lillois]
  • A. Laviolette
    Laviolette was a 17th-century French military officer and colonial administrator best known for establishing the settlement that became the city of Trois-Rivières in New France.
  • B. Orelle
    Orelle is a small French Alpine village and ski resort that serves as a quieter gateway into the vast Les Trois Vallées ski area.
  • C. Nantz
    Nantz is the surname of Jim Nantz, a prominent American sportscaster best known for his long-running work with CBS Sports covering events like the NFL, NCAA basketball, and The Masters.
  • D. Gavisse
    Gavisse is a small commune in northeastern France, located in the Moselle department near the border with Luxembourg and Germany.
  • E. Doncieux
    Doncieux is a French surname most notably associated with Camille Doncieux, the first wife and frequent model of painter Claude Monet.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lillois
Triple: [Picard, hasDialect, Lillois]
Generated description
Lillois is a regional dialect of the Picard language traditionally spoken in and around the city of Lille in northern France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lillois
Target entity description: Lillois is a regional dialect of the Picard language traditionally spoken in and around the city of Lille in northern France.
  • A. Laviolette
    Laviolette was a 17th-century French military officer and colonial administrator best known for establishing the settlement that became the city of Trois-Rivières in New France.
  • B. Orelle
    Orelle is a small French Alpine village and ski resort that serves as a quieter gateway into the vast Les Trois Vallées ski area.
  • C. Nantz
    Nantz is the surname of Jim Nantz, a prominent American sportscaster best known for his long-running work with CBS Sports covering events like the NFL, NCAA basketball, and The Masters.
  • D. Gavisse
    Gavisse is a small commune in northeastern France, located in the Moselle department near the border with Luxembourg and Germany.
  • E. Doncieux
    Doncieux is a French surname most notably associated with Camille Doncieux, the first wife and frequent model of painter Claude Monet.
  • F. None of above. chosen

Provenance (5 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_69d822ec69008190a9232caa68836872 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded291103c8190a64cfe700bfee197 completed April 14, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe64fe89e88190912cd205feef85d3 completed May 8, 2026, 10:34 p.m.
NEDg Description generation batch_69fe660250ec819084aed06983e0df06 completed May 8, 2026, 10:38 p.m.
NED2 Entity disambiguation (via description) batch_69fe667bed5c81909832d09228595533 completed May 8, 2026, 10:41 p.m.
Created at: April 10, 2026, 1:53 a.m.