Triple

T19036538
Position Surface form Disambiguated ID Type / Status
Subject Province of Ulster E465885 entity
Predicate hasAirport P105 FINISHED
Object Donegal 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: Donegal Airport | Statement: [Province of Ulster, hasAirport, Donegal Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donegal Airport
Context triple: [Province of Ulster, hasAirport, Donegal Airport]
  • A. Donegal Airport chosen
    Donegal Airport is a small regional airport in northwest Ireland that provides domestic and limited international flights, serving as an air gateway to the remote and scenic County Donegal.
  • B. Waterford Airport
    Waterford Airport is a regional airport in County Waterford, Ireland, providing air transport services to the southeast of the country.
  • C. Sligo Airport
    Sligo Airport is a small regional airport in County Sligo, Ireland, providing limited domestic and charter flight services.
  • D. Collinstown Airport
    Collinstown Airport was the original name of what is now Dublin Airport, Ireland’s main international airport serving the capital city.
  • E. Cork Airport
    Cork Airport is an international airport in County Cork, Ireland, serving as a key regional gateway and a secondary hub for Aer Lingus.
  • 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d744b39881909334a80a4c15000b completed April 20, 2026, 7:35 a.m.
Created at: April 10, 2026, 12:02 p.m.