Triple

T530922
Position Surface form Disambiguated ID Type / Status
Subject Beijing Capital International Airport E12219 entity
Predicate servesAsHubFor P423 FINISHED
Object XiamenAir E30720 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: XiamenAir | Statement: [Beijing Capital International Airport, servesAsHubFor, XiamenAir]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: XiamenAir
Context triple: [Beijing Capital International Airport, servesAsHubFor, XiamenAir]
  • A. XiamenAir chosen
    XiamenAir is a Chinese airline based in Xiamen that operates domestic and international flights across Asia and beyond.
  • B. 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.
  • C. Shenzhen Airlines
    Shenzhen Airlines is a major Chinese carrier based in Shenzhen that operates extensive domestic and regional flights across Asia.
  • D. China Southern Airlines
    China Southern Airlines is one of China’s largest airlines, operating extensive domestic and international routes from major hubs like Guangzhou and Beijing.
  • E. Air China
    Air China is the flag carrier and one of the largest airlines of the People's Republic of China, operating extensive domestic and international passenger and cargo services.
  • 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_69a4933208e88190891f5debab1b776d completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a494dda58c8190870305056838a2b2 completed March 1, 2026, 7:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4d03e47c08190b5e5e37402c6cd21 completed March 1, 2026, 11:48 p.m.
Created at: March 1, 2026, 7:32 p.m.