Triple
T6864592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ezaki Glico Co., Ltd. |
E158365
|
entity |
| Predicate | notableProduct |
P1448
|
FINISHED |
| Object | Pocky |
E623304
|
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: Pocky | Statement: [Ezaki Glico Co., Ltd., notableProduct, Pocky]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pocky Context triple: [Ezaki Glico Co., Ltd., notableProduct, Pocky]
-
A.
Pocky
chosen
Pocky is a popular Japanese snack consisting of thin biscuit sticks coated in flavored chocolate or other sweet coatings.
-
B.
Chocoballs
Chocoballs are a popular wizarding-world confectionery—chocolate sweets often filled with strawberry mousse—sold at Honeydukes in the Harry Potter series.
-
C.
Bisco
Bisco is a popular Japanese biscuit snack brand known for its cream-filled sandwich cookies marketed as a nutritious treat for children.
-
D.
Kachidoki
Kachidoki is a waterfront district in Tokyo’s Chūō ward known for its high-rise residential towers, proximity to the Sumida River, and convenient access to central Tokyo.
-
E.
Chicolini
Chicolini is a bumbling, fast-talking character played by Chico Marx in the Marx Brothers film "Duck Soup," serving as a comic foil in the political satire.
- 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_69c68830cdbc8190a8301c7a9d9f651a |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d88af6d88190ac9faa32fa1bfa0e |
completed | March 27, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7428b2fe88190ac1798922e2b9620 |
completed | March 28, 2026, 2:52 a.m. |
Created at: March 27, 2026, 2:21 p.m.