Triple

T10831812
Position Surface form Disambiguated ID Type / Status
Subject Santander E255638 entity
Predicate hasAirport P105 FINISHED
Object Santander Airport E609976 NE FINISHED

How this triple was built (2 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: Santander Airport | Statement: [Santander, hasAirport, Santander Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Santander Airport
Context triple: [Santander, hasAirport, Santander Airport]
  • A. Santander Airport chosen
    Santander Airport is a regional international airport serving the city of Santander and the Cantabria region in northern Spain.
  • B. Burgos Airport
    Burgos Airport is a regional public airport in Burgos, Spain, providing domestic air services and connecting the city to the national air transport network.
  • C. Valencia Airport
    Valencia Airport is an international airport serving the city of Valencia and the surrounding region on Spain’s eastern Mediterranean coast.
  • D. Jardines del Rey Airport
    Jardines del Rey Airport is the main international airport serving the resort island of Cayo Coco and the surrounding Jardines del Rey archipelago in Cuba.
  • E. La Rioja Airport
    La Rioja Airport is a regional public airport serving the city of La Rioja in northwestern Argentina, providing domestic flight connections for the surrounding province.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aa8081448190a9324184f2bd1c26 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7442323948190afd9488815f7908b completed April 9, 2026, 6:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb11a264c8190829ff89f0b13d063 completed April 14, 2026, 9:26 p.m.
Created at: April 8, 2026, 9:19 p.m.