Triple

T10460338
Position Surface form Disambiguated ID Type / Status
Subject Air Hong Kong E246654 entity
Predicate callsign P1565 FINISHED
Object AIR HONG KONG E49619 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: AIR HONG KONG | Statement: [Air Hong Kong, callsign, AIR HONG KONG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AIR HONG KONG
Context triple: [Air Hong Kong, callsign, AIR HONG KONG]
  • A. Air Hong Kong chosen
    Air Hong Kong is a Hong Kong-based all-cargo airline that primarily operates regional freight services across Asia.
  • B. Bangkok Airways
    Bangkok Airways is a regional airline based in Thailand that operates scheduled services across Asia, often marketing itself as a boutique carrier with full-service amenities.
  • C. Jin Air
    Jin Air is a South Korean low-cost airline that operates domestic and international passenger flights.
  • D. Hong Kong Airlines
    Hong Kong Airlines is a Hong Kong-based full-service carrier operating regional and international flights primarily across Asia and the Pacific.
  • E. EVA Air
    EVA Air is a major Taiwanese international airline known for its extensive global route network, high service standards, and innovative themed flights such as its Hello Kitty jets.
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d50882eb0c8190a4311634b867eab1 completed April 7, 2026, 1:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69d9882acd348190ae3ab2f17c834aef completed April 10, 2026, 11:30 p.m.
Created at: April 6, 2026, 12:18 p.m.