Triple

T10424702
Position Surface form Disambiguated ID Type / Status
Subject YY-20 E245755 entity
Predicate basedOn P98 FINISHED
Object Y-20 E254650 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: Y-20 | Statement: [YY-20, basedOn, Y-20]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Y-20
Context triple: [YY-20, basedOn, Y-20]
  • A. Y-20 chosen
    The Y-20 is a large Chinese military transport aircraft designed for strategic airlift of troops, equipment, and supplies over long distances.
  • B. Chengdu J-20
    The Chengdu J-20 is a Chinese fifth-generation stealth fighter jet designed for long-range air superiority and strike missions.
  • C. Chengdu J-10
    The Chengdu J-10 is a Chinese multirole, single-engine fighter aircraft designed for air superiority and ground attack missions.
  • D. KF-16
    The KF-16 is a South Korean–produced variant of the F-16 Fighting Falcon multirole fighter, built under license with localized systems and upgrades for the Republic of Korea Air Force.
  • E. J20
    The J20 is an early second-generation Toyota Land Cruiser series known for its more refined body design and improved comfort over the original models while retaining strong off-road capability.
  • 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_69d381bf3dc08190bf35a2643e4e8f22 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea47a6408190a87b32760692487f completed April 7, 2026, 11:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7fc2160208190b6384190d9537df4 completed April 9, 2026, 7:21 p.m.
Created at: April 6, 2026, 12:12 p.m.