Triple

T6840599
Position Surface form Disambiguated ID Type / Status
Subject La Rioja E157561 entity
Predicate hasGrapeVariety P33546 FINISHED
Object Viura
Viura is a white grape variety from Spain, best known as the primary grape used in the white wines of Rioja and often referred to as Macabeo in other regions.
 E623795 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: Viura | Statement: [La Rioja, hasGrapeVariety, Viura]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Viura
Context triple: [La Rioja, hasGrapeVariety, Viura]
  • A. Vinaròs
    Vinaròs is a coastal town in the province of Castellón, Spain, known for its fishing port, beaches, and historic role in the Spanish Civil War.
  • B. Rabassa
    Rabassa is a surname most notably associated with Gregory Rabassa, the acclaimed American translator of Latin American literature.
  • C. Vernazobre
    Vernazobre is a river in southern France that serves as a tributary of the Orb.
  • D. Vegueta
    Vegueta is the historic old quarter of Las Palmas de Gran Canaria, known for its colonial architecture, cobbled streets, and cultural landmarks.
  • E. Illueca
    Illueca is a small town in the province of Zaragoza, Aragon, Spain, known historically as the birthplace of Pope Benedict XIII (Pedro de Luna).
  • 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: Viura
Triple: [La Rioja, hasGrapeVariety, Viura]
Generated description
Viura is a white grape variety from Spain, best known as the primary grape used in the white wines of Rioja and often referred to as Macabeo in other regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Viura
Target entity description: Viura is a white grape variety from Spain, best known as the primary grape used in the white wines of Rioja and often referred to as Macabeo in other regions.
  • A. Vinaròs
    Vinaròs is a coastal town in the province of Castellón, Spain, known for its fishing port, beaches, and historic role in the Spanish Civil War.
  • B. Rabassa
    Rabassa is a surname most notably associated with Gregory Rabassa, the acclaimed American translator of Latin American literature.
  • C. Vernazobre
    Vernazobre is a river in southern France that serves as a tributary of the Orb.
  • D. Vegueta
    Vegueta is the historic old quarter of Las Palmas de Gran Canaria, known for its colonial architecture, cobbled streets, and cultural landmarks.
  • E. Illueca
    Illueca is a small town in the province of Zaragoza, Aragon, Spain, known historically as the birthplace of Pope Benedict XIII (Pedro de Luna).
  • 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_69c6882c53608190b99aebef079b23bd completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d6b4a1f88190b4f532828697fbd8 completed March 27, 2026, 7:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c72fb4f80081908198c8270633d34a completed March 28, 2026, 1:32 a.m.
NEDg Description generation batch_69c730cdb3c88190802ddda15d8aa52f completed March 28, 2026, 1:37 a.m.
NED2 Entity disambiguation (via description) batch_69c734876ca0819087842bec6e01c02e completed March 28, 2026, 1:53 a.m.
Created at: March 27, 2026, 2:19 p.m.