Triple
T19530498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soju |
E488640
|
entity |
| Predicate | isOftenConsumedWith |
P104841
|
FINISHED |
| Object | Korean barbecue |
—
|
LITERAL 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: Korean barbecue | Statement: [Soju, isOftenConsumedWith, Korean barbecue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOftenConsumedWith Context triple: [Soju, isOftenConsumedWith, Korean barbecue]
-
A.
commonlyConsumedAt
chosen
Indicates that one entity is typically eaten or drunk during, or in association with, a particular time, event, or context.
-
B.
isTypicallyConsumedFrom
Indicates that one entity is most commonly eaten or drunk using, contained in, or taken from the other entity.
-
C.
drinksWith
Indicates that two entities consume beverages together, typically at the same time and place in a social context.
-
D.
isOftenPurchasedAs
Indicates that one item is frequently bought together with, or in conjunction with, another item.
-
E.
notablyUsedWith
Indicates that one entity is commonly or prominently used together with another entity, in a way that is especially characteristic or noteworthy.
- F. None of above.
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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6363ec6cc8190b9e9ac0196b288f9 |
completed | April 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.