Triple

T14948427
Position Surface form Disambiguated ID Type / Status
Subject Air Do E372727 entity
Predicate focusAirport P8171 FINISHED
Object Tokyo Haneda Airport E35463 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: Tokyo Haneda Airport | Statement: [Air Do, focusAirport, Tokyo Haneda Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tokyo Haneda Airport
Context triple: [Air Do, focusAirport, Tokyo Haneda Airport]
  • A. Haneda Airport chosen
    Haneda Airport is one of Tokyo’s primary international airports and one of Japan’s busiest air travel hubs.
  • B. Narita International Airport
    Narita International Airport is a major international gateway to Japan and one of the primary airports serving the Greater Tokyo area.
  • C. Naha–Tokyo Haneda
    Naha–Tokyo Haneda is a major domestic air route in Japan connecting Okinawa’s capital Naha with Tokyo’s centrally located Haneda Airport.
  • D. Miyazaki–Tokyo Haneda
    Miyazaki–Tokyo Haneda is a domestic air route in Japan connecting Miyazaki Airport on Kyushu with Tokyo’s centrally located Haneda Airport.
  • E. Kansai International Airport
    Kansai International Airport is a major international airport in Japan built on an artificial island in Osaka Bay, serving as a key gateway to the Kansai region.
  • 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_69d85cca979481908747d2a81eba1cea completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded68e35c481908e47cd68441c5115 completed April 15, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d39a0908190a27f7bbaee7a04ef completed May 9, 2026, 1:57 p.m.
Created at: April 10, 2026, 2:39 a.m.