Triple
T23693343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Okryu Restaurant |
E585364
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Korean restaurant |
C45749
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: Korean restaurant Context triple: [Okryu Restaurant, instanceOf, Korean restaurant]
-
A.
Chinese restaurant
A Chinese restaurant is a dining establishment that specializes in preparing and serving Chinese cuisine, often featuring regional dishes, traditional cooking techniques, and culturally themed decor.
-
B.
Korean food
Korean food is a diverse cuisine characterized by bold flavors, fermented ingredients like kimchi, and a balance of spicy, savory, and umami dishes often served with rice and numerous side dishes.
-
C.
Asian restaurant
chosen
An Asian restaurant is a dining establishment that specializes in preparing and serving cuisines originating from Asian countries, such as Chinese, Japanese, Korean, Thai, Vietnamese, or Indian food.
-
D.
Japanese restaurant
A Japanese restaurant is a dining establishment that specializes in preparing and serving traditional and contemporary Japanese cuisine, such as sushi, sashimi, ramen, tempura, and bento, often emphasizing fresh ingredients, seasonal dishes, and meticulous presentation.
-
E.
Thai restaurant
A Thai restaurant is a dining establishment that specializes in serving traditional and contemporary Thai cuisine, often featuring bold flavors, aromatic herbs, and a balance of sweet, sour, salty, and spicy dishes.
- F. None of above.
Provenance (1 batch)
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_69e249037ce0819088b149608e98f685 |
completed | April 17, 2026, 2:51 p.m. |
Created at: April 17, 2026, 6:52 p.m.