Triple

T9774945
Position Surface form Disambiguated ID Type / Status
Subject Kobelco Steelers E237222 entity
Predicate owner P347 FINISHED
Object Kobe Steel E819666 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: Kobe Steel | Statement: [Kobelco Steelers, owner, Kobe Steel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kobe Steel
Context triple: [Kobelco Steelers, owner, Kobe Steel]
  • A. Kobe Steel chosen
    Kobe Steel is a major Japanese steel manufacturer and industrial conglomerate known for producing steel, aluminum, and machinery under the brand name Kobelco.
  • B. Mitsubishi Steel Mfg
    Mitsubishi Steel Mfg is a Japanese manufacturer specializing in steel products and components, operating as part of the broader Mitsubishi corporate group.
  • C. Kaiser Steel
    Kaiser Steel was a major American steel-producing company that played a significant role in U.S. industrial and wartime production in the mid-20th century.
  • D. Sumitomo Corporation
    Sumitomo Corporation is a major Japanese multinational trading and investment company and one of the core members of the Sumitomo Group conglomerate.
  • E. Hayakawa Metal Works
    Hayakawa Metal Works was the original manufacturing company founded by Tokuji Hayakawa in Japan that later evolved into the global electronics firm Sharp Corporation.
  • 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_69ca84d975a08190aab25b02a89bdab3 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda13148288190bcbb3b4a066d9fc1 completed April 1, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c41789548190ba4f6fdd7fb5192a completed April 5, 2026, 2:08 a.m.
Created at: March 30, 2026, 8:26 p.m.