Triple

T4613041
Position Surface form Disambiguated ID Type / Status
Subject Tiger Woods E100802 entity
Predicate sponsor P67 FINISHED
Object Bridgestone Golf E74512 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: Bridgestone Golf | Statement: [Tiger Woods, sponsor, Bridgestone Golf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bridgestone Golf
Context triple: [Tiger Woods, sponsor, Bridgestone Golf]
  • A. Bridgestone chosen
    Bridgestone is a global tire and rubber company headquartered in Japan, known for its extensive involvement in motorsports and major sports sponsorships.
  • B. Golf Company
    Golf Company is a rifle company within the U.S. Marine Corps’ 2nd Battalion, 4th Marines, known for its role in infantry combat operations.
  • C. Dunlop
    Dunlop is a well-known tire manufacturer that produces high-performance motorcycle and automotive tires used in both professional racing and everyday driving.
  • D. Toyo Kogyo Co., Ltd.
    Toyo Kogyo Co., Ltd. was the original corporate name of the Japanese automaker now known as Mazda Motor Corporation.
  • E. Nokian Footwear
    Nokian Footwear is a Finnish company best known for its durable rubber boots and outdoor footwear, originating from the industrial heritage of the town of Nokia.
  • 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_69bd43cf363c819087fd5ab441b4a3f4 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd59c11f5481909f61e23503711cf5 completed March 20, 2026, 2:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfa895b7481909e54cfa56a54c8dc completed March 21, 2026, 1:55 a.m.
Created at: March 20, 2026, 1:12 p.m.