Triple

T18863565
Position Surface form Disambiguated ID Type / Status
Subject Air Kiribati E461374 entity
Predicate ICAOCode P419 FINISHED
Object AKL 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: AKL | Statement: [Air Kiribati, ICAOCode, AKL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AKL
Context triple: [Air Kiribati, ICAOCode, AKL]
  • A. Auckland chosen
    Auckland is a major New Zealand metropolis known for its harbors, multicultural population, and role as the country’s primary economic and transport hub.
  • B. Tokua Airport
    Tokua Airport is the main commercial airport serving East New Britain Province in Papua New Guinea, acting as the primary air gateway to the regional center of Kokopo and nearby Rabaul.
  • C. Naujaat Airport
    Naujaat Airport is a small public airport in Naujaat, Nunavut, Canada, providing vital air transport links for passengers and cargo to this remote Arctic community.
  • D. Aucklander
    An Aucklander is a resident or native of Auckland, the largest city in New Zealand.
  • E. Coraki
    Coraki is a small town in northern New South Wales, Australia, situated at the junction of the Richmond and Wilsons rivers.
  • 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_69d8dcfb7b9c8190854e7b171b98ea2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c2a304d4819092f14b7932d01afe completed April 20, 2026, 6:07 a.m.
Created at: April 10, 2026, 11:57 a.m.