Triple
T22441443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yuxiang eggplant |
E554762
|
entity |
| Predicate | commonPreparationStep |
P103029
|
FINISHED |
| Object | salting eggplant before cooking |
—
|
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: salting eggplant before cooking | Statement: [Yuxiang eggplant, commonPreparationStep, salting eggplant before cooking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonPreparationStep Context triple: [Yuxiang eggplant, commonPreparationStep, salting eggplant before cooking]
-
A.
commonPreparationMethod
chosen
Indicates that two or more items share the same typical way of being prepared or processed.
-
B.
typicalPreparation
Indicates the usual or standard way in which something is prepared or made.
-
C.
recommendedPreparation
Indicates that one entity is suggested or advised as a suitable preparation or prerequisite for engaging with another entity.
-
D.
meatPreparation
Indicates the method or process by which meat is treated, cooked, or otherwise prepared for consumption.
-
E.
preparationBegan
Indicates that the initial actions or processes required for something to be carried out or occur have started.
- 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_69e11e5010e48190ae1e9c9db9697637 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ae1f82881908a611f134eb03f3d |
completed | April 29, 2026, 1:12 a.m. |
| PD | Predicate disambiguation | batch_69e898a327948190beee5e168006a0a7 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:47 p.m.