Triple

T22096343
Position Surface form Disambiguated ID Type / Status
Subject Limerick City E546042 entity
Predicate hasAirportNearby P4363 FINISHED
Object Shannon 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: Shannon Airport | Statement: [Limerick City, hasAirportNearby, Shannon Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shannon Airport
Context triple: [Limerick City, hasAirportNearby, Shannon Airport]
  • A. Shannon Airport chosen
    Shannon Airport is a major international airport in western Ireland known for its transatlantic services and historic role in pioneering global air travel.
  • B. Wa Airport
    Wa Airport is a regional public airport serving the city of Wa and its surrounding areas in the Upper West Region of Ghana.
  • C. Newman Airport
    Newman Airport is a regional airport in Western Australia that primarily serves the mining town of Newman and its surrounding Pilbara region.
  • D. Mwanza Airport
    Mwanza Airport is a regional airport in Mwanza, Tanzania, serving as a key hub for domestic flights and connections around Lake Victoria.
  • E. Churchill Airport
    Churchill Airport is a regional airport in Churchill, Manitoba, Canada, serving as a key transportation hub for the remote northern community and access point for polar bear and Arctic tourism.
  • 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_69e11e36d03c8190a83a1ba802b7231b completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128e8f1f48190a5f1d9e96a6de688 completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:30 p.m.