Triple

T6320525
Position Surface form Disambiguated ID Type / Status
Subject Otago E141724 entity
Predicate hasAirport P105 FINISHED
Object Dunedin Airport E398487 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: Dunedin Airport | Statement: [Otago, hasAirport, Dunedin Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dunedin Airport
Context triple: [Otago, hasAirport, Dunedin Airport]
  • A. Dunedin Airport chosen
    Dunedin Airport is a regional international airport serving the city of Dunedin and the wider Otago region in New Zealand’s South Island.
  • B. Invercargill Airport
    Invercargill Airport is a regional airport in New Zealand serving the city of Invercargill and the wider Southland region with domestic flights and aviation services.
  • C. Greymouth Airport
    Greymouth Airport is a small regional airfield serving the town of Greymouth on the West Coast of New Zealand’s South Island.
  • D. Nelson Airport
    Nelson Airport is a regional airport in Nelson, New Zealand, serving as a key domestic hub with frequent connections to major New Zealand cities.
  • E. Wellington Airport
    Wellington Airport is the main international and domestic airport serving New Zealand’s capital city, Wellington, on the southern tip of the North Island.
  • 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_69c008d13b8c8190be47d896eb735605 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c064c61f008190b316b9ff1023b057 completed March 22, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5e48485308190adc2208ad46faaa7 completed March 27, 2026, 1:59 a.m.
Created at: March 22, 2026, 4:29 p.m.