Triple

T15734089
Position Surface form Disambiguated ID Type / Status
Subject Bonnievale Wines E381421 entity
Predicate grapeVarietyUsed P975 FINISHED
Object Colombar
Colombar is a white wine grape variety, also known as Colombard, commonly used for producing crisp, fruity wines and brandies.
 E1173461 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: Colombar | Statement: [Bonnievale Wines, grapeVarietyUsed, Colombar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Colombar
Context triple: [Bonnievale Wines, grapeVarietyUsed, Colombar]
  • A. Ostabat
    Ostabat is a village in southwestern France known as a historic convergence point for several major pilgrimage routes to Santiago de Compostela.
  • B. Vallromanes
    Vallromanes is a small municipality in the province of Barcelona, Catalonia, known for its natural surroundings, golf course, and proximity to the coastal and metropolitan areas.
  • C. Goubellat
    Goubellat is a town in northern Tunisia located within the Béja Governorate, known primarily for its agricultural surroundings and rural character.
  • D. Crocetta
    Crocetta is an underground station on Milan’s Metro Line 3 serving the central area of the city.
  • E. La Cremà
    La Cremà is the climactic night of Valencia’s Las Fallas festival when the elaborate fallas monuments are dramatically burned in large public bonfires.
  • 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: Colombar
Triple: [Bonnievale Wines, grapeVarietyUsed, Colombar]
Generated description
Colombar is a white wine grape variety, also known as Colombard, commonly used for producing crisp, fruity wines and brandies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Colombar
Target entity description: Colombar is a white wine grape variety, also known as Colombard, commonly used for producing crisp, fruity wines and brandies.
  • A. Ostabat
    Ostabat is a village in southwestern France known as a historic convergence point for several major pilgrimage routes to Santiago de Compostela.
  • B. Vallromanes
    Vallromanes is a small municipality in the province of Barcelona, Catalonia, known for its natural surroundings, golf course, and proximity to the coastal and metropolitan areas.
  • C. Goubellat
    Goubellat is a town in northern Tunisia located within the Béja Governorate, known primarily for its agricultural surroundings and rural character.
  • D. Crocetta
    Crocetta is an underground station on Milan’s Metro Line 3 serving the central area of the city.
  • E. La Cremà
    La Cremà is the climactic night of Valencia’s Las Fallas festival when the elaborate fallas monuments are dramatically burned in large public bonfires.
  • 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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fd586a88190aa1b1b88368d386f completed April 16, 2026, 2:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff8300a4248190ba52573b57f31b36 completed May 9, 2026, 6:54 p.m.
NEDg Description generation batch_69ff8378450081909614f68772a23851 completed May 9, 2026, 6:56 p.m.
NED2 Entity disambiguation (via description) batch_69ff84125e808190a4d465d9effad639 completed May 9, 2026, 6:59 p.m.
Created at: April 10, 2026, 4:46 a.m.