Triple

T19116876
Position Surface form Disambiguated ID Type / Status
Subject T'way Air E467929 entity
Predicate callsign P1565 FINISHED
Object TWAY AIR 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: TWAY AIR | Statement: [T'way Air, callsign, TWAY AIR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TWAY AIR
Context triple: [T'way Air, callsign, TWAY AIR]
  • A. Tʼway Air chosen
    Tʼway Air is a South Korean low-cost airline operating domestic and international routes across Asia and the Pacific.
  • B. West Air
    West Air is a Chinese low-cost airline based in Chongqing that operates domestic and regional passenger services.
  • C. Winair
    Winair is a regional Caribbean airline based in Sint Maarten that operates short-haul flights to nearby islands, including serving the famously short-runway Juancho E. Yrausquin Airport on Saba.
  • D. McGee Airways
    McGee Airways was an early Alaskan airline founded in the 1930s that evolved through mergers and rebranding into what is now Alaska Airlines.
  • E. TACA Airlines
    TACA Airlines was a major Central American airline based in El Salvador that operated an extensive regional and international route network before merging with Avianca.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e399a6d8819090a9501ff1637b9d completed April 20, 2026, 8:28 a.m.
Created at: April 10, 2026, 12:05 p.m.