Triple

T1373053
Position Surface form Disambiguated ID Type / Status
Subject Okinawa Prefecture E30155 entity
Predicate hasAirport P105 FINISHED
Object Naha Airport E90732 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: Naha Airport | Statement: [Okinawa Prefecture, hasAirport, Naha Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Naha Airport
Context triple: [Okinawa Prefecture, hasAirport, Naha Airport]
  • A. Naha Airport chosen
    Naha Airport is the main commercial airport serving Okinawa Prefecture in Japan, acting as a key domestic and regional hub in the Ryukyu Islands.
  • B. Hana Airport
    Hana Airport is a small regional airport serving the remote town of Hāna on the eastern coast of Maui, Hawaii.
  • C. Gando Airport
    Gando Airport is the main international airport serving Gran Canaria in Spain’s Canary Islands.
  • D. Tajima Airport
    Tajima Airport is a regional airport in northern Hyogo Prefecture, Japan, primarily serving domestic flights and connecting the Tajima area with major Japanese cities.
  • E. Mataveri International Airport
    Mataveri International Airport is the remote international airport serving Easter Island, known as one of the most isolated airports in the world and a key link between the island and mainland Chile.
  • 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_69a498f912008190a376a98b207b2071 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c2f4889881908103473a0173e23f completed March 1, 2026, 10:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad01518d5481908cf14b24dde8342b completed March 8, 2026, 4:55 a.m.
Created at: March 1, 2026, 7:57 p.m.