Triple

T13175486
Position Surface form Disambiguated ID Type / Status
Subject Rías Baixas E313086 entity
Predicate wineClassification P12905 FINISHED
Object DO
DO (Denominación de Origen) is a Spanish quality classification that designates and protects wines from specific geographic regions with regulated production standards.
 E1025249 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: DO | Statement: [Rías Baixas, wineClassification, DO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DO
Context triple: [Rías Baixas, wineClassification, DO]
  • A. DO
    DO is the two-letter ISO 3166-1 alpha-2 country code assigned to the Dominican Republic.
  • B. DO
    DO is the official vehicle registration code used on license plates for the German city of Dortmund.
  • C. D0
    D0 is a major particle physics detector experiment at Fermilab’s Tevatron collider, designed to study high-energy proton–antiproton collisions and probe fundamental particles and forces.
  • D. OD
    OD is the commonly used abbreviation for the Open Definition, a standard that sets out principles for what qualifies as open data and open content.
  • E. OD
    OD is the abbreviation for the Ordedienst, a Dutch underground resistance organization that operated during World War II.
  • 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: DO
Triple: [Rías Baixas, wineClassification, DO]
Generated description
DO (Denominación de Origen) is a Spanish quality classification that designates and protects wines from specific geographic regions with regulated production standards.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DO
Target entity description: DO (Denominación de Origen) is a Spanish quality classification that designates and protects wines from specific geographic regions with regulated production standards.
  • A. DO
    DO is the two-letter ISO 3166-1 alpha-2 country code assigned to the Dominican Republic.
  • B. DO
    DO is the official vehicle registration code used on license plates for the German city of Dortmund.
  • C. D0
    D0 is a major particle physics detector experiment at Fermilab’s Tevatron collider, designed to study high-energy proton–antiproton collisions and probe fundamental particles and forces.
  • D. OD
    OD is the commonly used abbreviation for the Open Definition, a standard that sets out principles for what qualifies as open data and open content.
  • E. OD
    OD is the abbreviation for the Ordedienst, a Dutch underground resistance organization that operated during World War II.
  • 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_69d806ac3ee081909b2fd27d060aa974 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c303e3c819086cf0f0b6d9e61ca completed April 10, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eafe03c48190992df41f77fb043e completed May 3, 2026, 6:28 a.m.
NEDg Description generation batch_69f6f02dcce88190bdb07e271a52729a completed May 3, 2026, 6:50 a.m.
NED2 Entity disambiguation (via description) batch_69f6f09ff1088190812008373c0553d5 completed May 3, 2026, 6:52 a.m.
Created at: April 9, 2026, 9:14 p.m.