Triple

T1957255
Position Surface form Disambiguated ID Type / Status
Subject Basque E42297 entity
Predicate hasDialect P4251 FINISHED
Object Souletin
Souletin is a distinct dialect of the Basque language traditionally spoken in the Soule (Zuberoa) region of the French Basque Country.
 E218534 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: Souletin | Statement: [Basque, hasDialect, Souletin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Souletin
Context triple: [Basque, hasDialect, Souletin]
  • A. Bougros
    Bougros is one of the prestigious Grand Cru vineyard sites in the Chablis wine region of Burgundy, France, known for producing high-quality Chardonnay wines.
  • B. Chardonel
    Chardonel is a hybrid white wine grape variety known for its cold hardiness and Chardonnay-like character, widely grown in cool-climate American wine regions.
  • C. Soral
    Soral is a small rural municipality in southwestern Switzerland, located in the canton of Geneva near the French border.
  • D. Margeride
    Margeride is a mountainous and sparsely populated region in south-central France known for its granite plateaus, forests, and traditional rural landscapes.
  • E. La Sablonière
    La Sablonière is one of the small islets within the Les Écréhous reef and island group off the coast of Jersey in the Channel Islands.
  • 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: Souletin
Triple: [Basque, hasDialect, Souletin]
Generated description
Souletin is a distinct dialect of the Basque language traditionally spoken in the Soule (Zuberoa) region of the French Basque Country.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Souletin
Target entity description: Souletin is a distinct dialect of the Basque language traditionally spoken in the Soule (Zuberoa) region of the French Basque Country.
  • A. Bougros
    Bougros is one of the prestigious Grand Cru vineyard sites in the Chablis wine region of Burgundy, France, known for producing high-quality Chardonnay wines.
  • B. Chardonel
    Chardonel is a hybrid white wine grape variety known for its cold hardiness and Chardonnay-like character, widely grown in cool-climate American wine regions.
  • C. Soral
    Soral is a small rural municipality in southwestern Switzerland, located in the canton of Geneva near the French border.
  • D. Margeride
    Margeride is a mountainous and sparsely populated region in south-central France known for its granite plateaus, forests, and traditional rural landscapes.
  • E. La Sablonière
    La Sablonière is one of the small islets within the Les Écréhous reef and island group off the coast of Jersey in the Channel Islands.
  • 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_69a8870eea088190a38781990812a9bc completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb37c60148190823f6a2a73b949e8 completed March 7, 2026, 5:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69adfbcc9ba48190985f48dbef1f2d94 completed March 8, 2026, 10:44 p.m.
NEDg Description generation batch_69adfc6bd8e08190a065a89ab3412126 completed March 8, 2026, 10:47 p.m.
NED2 Entity disambiguation (via description) batch_69adfcee414c8190b1a0574f6bd55602 completed March 8, 2026, 10:49 p.m.
Created at: March 4, 2026, 7:36 p.m.