Triple
T8036587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marui Group |
E187122
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object | Epos Card Co., Ltd. |
E703221
|
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: Epos Card Co., Ltd. | Statement: [Marui Group, hasSubsidiary, Epos Card Co., Ltd.]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Epos Card Co., Ltd. Context triple: [Marui Group, hasSubsidiary, Epos Card Co., Ltd.]
-
A.
エポスカード
chosen
エポスカードは、丸井グループ系のクレジットカードブランドで、ショッピングや飲食などでのポイント還元や優待特典が充実しているカードサービスです。
-
B.
JCB Co., Ltd.
JCB Co., Ltd. is a major Japanese credit card company and payment brand that helped establish global security standards for the payment card industry.
-
C.
A-EON Technology Ltd
A-EON Technology Ltd is a company known for developing and marketing modern PowerPC-based hardware and related products for the AmigaOS computing community.
-
D.
Worldline
Worldline is a French multinational company specializing in payment and transactional services, recognized as a major European player in digital payments.
-
E.
Metcard
Metcard was Melbourne’s former magnetic stripe ticketing system used for public transport before the introduction of the Myki smartcard.
- 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_69ca82ae2d1081909dbfee42b41db419 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3f188e1c8190b92760c91d31f2df |
completed | March 31, 2026, 3:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc56fa97ac8190a0bd646d9ec345e4 |
completed | March 31, 2026, 11:21 p.m. |
Created at: March 30, 2026, 5:22 p.m.