Triple

T8028451
Position Surface form Disambiguated ID Type / Status
Subject HND E186914 entity
Predicate focusCityFor P164 FINISHED
Object Skymark Airlines E190855 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: Skymark Airlines | Statement: [HND, focusCityFor, Skymark Airlines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Skymark Airlines
Context triple: [HND, focusCityFor, Skymark Airlines]
  • A. Skymark Airlines chosen
    Skymark Airlines is a Japanese low-cost carrier based in Tokyo that operates domestic flights and some international services.
  • B. Ryukyu Air Commuter
    Ryukyu Air Commuter is a Japanese regional airline that operates commuter flights primarily within the Okinawa Prefecture and surrounding islands.
  • C. Amakusa Airlines
    Amakusa Airlines is a small Japanese regional airline based in Kumamoto Prefecture that operates domestic routes connecting remote islands and regional cities.
  • D. Wasaya Airways
    Wasaya Airways is a Canadian regional airline based in northern Ontario that primarily provides passenger and cargo services to remote First Nations and northern communities.
  • E. Jeju Air
    Jeju Air is a South Korean low-cost airline that operates extensive domestic and international routes, particularly serving leisure and regional markets in East Asia.
  • 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_69ca82ad4e2c8190a693e3c9e30fe66f completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3ecdbc5881909246982b93978841 completed March 31, 2026, 3:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc93bc11108190a34a35d0022f4bfd completed April 1, 2026, 3:40 a.m.
Created at: March 30, 2026, 5:21 p.m.