Triple
T22244658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yonex |
E549810
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object | Yonex Co., Ltd. USA |
—
|
NE NERFINISHED |
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: Yonex Co., Ltd. USA | Statement: [Yonex, hasSubsidiary, Yonex Co., Ltd. USA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yonex Co., Ltd. USA Context triple: [Yonex, hasSubsidiary, Yonex Co., Ltd. USA]
-
A.
Yonex
chosen
Yonex is a Japanese sports equipment manufacturer best known for its high-quality badminton, tennis, and golf products used by many professional athletes.
-
B.
Babolat
Babolat is a French sports equipment company best known for its high-performance tennis racquets and strings used by many top professional players.
-
C.
Daiwa House Industry
Daiwa House Industry is a major Japanese construction and real estate development company known for large-scale commercial, residential, and mixed-use projects.
-
D.
Mizuno
Mizuno is a Japanese sports equipment and sportswear company known for producing high-quality gear and apparel for a wide range of sports.
-
E.
Yoki, Inc.
Yoki, Inc. is a film and television production company known for developing and producing screen content such as the project titled "The King."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e41d9408190bd770cf282e22753 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f132170e5081909b9dbb204abf2a45 |
completed | April 28, 2026, 10:17 p.m. |
Created at: April 16, 2026, 8:38 p.m.