Triple

T759213
Position Surface form Disambiguated ID Type / Status
Subject MARC E16027 entity
Predicate usesRollingStockFrom P5426 FINISHED
Object Kawasaki E85096 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: Kawasaki | Statement: [MARC, usesRollingStockFrom, Kawasaki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kawasaki
Context triple: [MARC, usesRollingStockFrom, Kawasaki]
  • A. Kawasaki
    Kawasaki is a major industrial and residential city in Kanagawa Prefecture, Japan, located between Tokyo and Yokohama along the Tama River.
  • B. Suzuki Motor Corporation
    Suzuki Motor Corporation is a Japanese multinational automaker best known for its compact cars, motorcycles, and all-terrain vehicles sold worldwide.
  • C. Kawasaki Heavy Industries chosen
    Kawasaki Heavy Industries is a major Japanese multinational corporation known for manufacturing ships, heavy machinery, aerospace equipment, and transportation systems.
  • D. Harley-Davidson
    Harley-Davidson is an iconic American motorcycle manufacturer renowned for its heavyweight cruiser bikes, distinctive V-twin engines, and strong biker subculture.
  • E. Ducati
    Ducati is an Italian motorcycle manufacturer renowned for its high-performance sport bikes, racing heritage, and distinctive design.
  • 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_69a493684ee48190bd43b7c78da4aec8 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4aa9cecd08190a23c9f65080a4ac7 completed March 1, 2026, 9:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69a673345f18819084e2caf380e46b30 completed March 3, 2026, 5:35 a.m.
Created at: March 1, 2026, 7:37 p.m.