Triple
T27808767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teochew beef hotpot |
E702461
|
entity |
| Predicate | dippingSauce |
P51950
|
FINISHED |
| Object | fermented bean curd sauce |
—
|
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: fermented bean curd sauce | Statement: [Teochew beef hotpot, dippingSauce, fermented bean curd sauce]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dippingSauce Context triple: [Teochew beef hotpot, dippingSauce, fermented bean curd sauce]
-
A.
sauceType
chosen
Indicates the specific kind or category of sauce associated with an item or dish.
-
B.
isTypicallyGarnishedWith
Indicates that one item is commonly used as a garnish or decorative finishing element for another.
-
C.
seasoningType
Indicates the specific kind or category of seasoning associated with an item or preparation.
-
D.
servesDish
Indicates that one entity prepares and presents a specific dish as food for another entity.
-
E.
typicalSauceConsistency
Indicates that something has the usual or characteristic thickness or texture expected of a sauce.
- 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_69ef840a16748190926719ab96120bae |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f63b317e048190963989b732b25b91 |
completed | May 2, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69f6370ea79c81909b761821ee0fa698 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 5:41 p.m.