Triple

T10412485
Position Surface form Disambiguated ID Type / Status
Subject Air China E245425 entity
Predicate hasSubsidiary P254 FINISHED
Object Dalian Airlines E252165 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: Dalian Airlines | Statement: [Air China, hasSubsidiary, Dalian Airlines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dalian Airlines
Context triple: [Air China, hasSubsidiary, Dalian Airlines]
  • A. Dalian Airlines chosen
    Dalian Airlines is a Chinese regional airline based in Dalian that operates domestic passenger services as a subsidiary of Air China.
  • B. Shanghai Airlines
    Shanghai Airlines is a Chinese airline based in Shanghai that operates domestic and international passenger flights as a subsidiary of China Eastern Airlines.
  • C. Donghai Airlines
    Donghai Airlines is a Chinese passenger and cargo airline based in Shenzhen that operates domestic and regional flights.
  • D. Xiamen Airlines
    Xiamen Airlines is a major Chinese passenger airline based in Xiamen, Fujian, operating extensive domestic and regional routes, including services across East and Southeast Asia.
  • E. Hainan Airlines
    Hainan Airlines is a major Chinese airline headquartered in Haikou, known for its extensive domestic and international route network and high service quality ratings.
  • 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_69d381be340c8190b05998703d42d224 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea0e17f081908fb16425f65e5808 completed April 7, 2026, 11:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69d8dc2b06188190ad399e1b5a545aec completed April 10, 2026, 11:16 a.m.
Created at: April 6, 2026, 12:10 p.m.