Triple
T29915999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cantonese stir-fried water spinach with fermented bean curd |
E759796
|
entity |
| Predicate | secondaryFlavorProfile |
P104049
|
FINISHED |
| Object | tangy |
—
|
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: tangy | Statement: [Cantonese stir-fried water spinach with fermented bean curd, secondaryFlavorProfile, tangy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryFlavorProfile Context triple: [Cantonese stir-fried water spinach with fermented bean curd, secondaryFlavorProfile, tangy]
-
A.
secondaryAroma
Indicates that an entity has a secondary or supporting aroma characteristic in addition to its primary scent.
-
B.
primaryFlavor
Indicates the dominant or most characteristic taste associated with an item relative to other possible flavors.
-
C.
hasSecondaryFlavor
chosen
Indicates that an entity possesses an additional, subordinate flavor characteristic beyond its primary flavor.
-
D.
secondaryFood
Indicates that one entity serves as a secondary or supplementary food source in relation to another entity.
-
E.
secondaryTone
Indicates that one tone functions as a secondary or supporting tonal element in relation to a primary tone within a given context.
- 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_69f2246189fc8190996b63ee1f9a2374 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fd884cb2b48190b6acd473430d9e19 |
completed | May 8, 2026, 6:53 a.m. |
| PD | Predicate disambiguation | batch_69fd8709ca208190a8bab836f0156af5 |
completed | May 8, 2026, 6:47 a.m. |
Created at: April 29, 2026, 6:12 p.m.