Triple

T19418767
Position Surface form Disambiguated ID Type / Status
Subject Barraigh E485788 entity
Predicate hasAirport P105 FINISHED
Object Barra Airport NE NERFINISHED

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: Barra Airport | Statement: [Barraigh, hasAirport, Barra Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barra Airport
Context triple: [Barraigh, hasAirport, Barra Airport]
  • A. Barra Airport chosen
    Barra Airport is a unique Scottish airport on the island of Barra, famous for its tidal beach runway where scheduled flights land directly on the sand.
  • B. Pedro Bay Airport
    Pedro Bay Airport is a small public-use airfield serving the remote community of Pedro Bay in Alaska, primarily providing regional and bush air service.
  • C. Isla Grande Airport
    Isla Grande Airport is a regional airport in San Juan, Puerto Rico, serving general aviation, charter, and some commercial flights near the city's convention and cruise ship districts.
  • D. Mitú Airport
    Mitú Airport is a regional public airport serving the remote town of Mitú in Colombia’s Vaupés Department, providing vital air connectivity to this isolated Amazonian area.
  • E. Panguilemo Airport
    Panguilemo Airport is a regional public airport serving the city of Talca and the surrounding Maule Region in central Chile.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62afbaf0c8190913eda4b04efbe67 completed April 20, 2026, 1:32 p.m.
Created at: April 10, 2026, 1:37 p.m.