Triple
T7825145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hakka cuisine |
E181226
|
entity |
| Predicate | knownForDish |
P79219
|
FINISHED |
| Object | Hakka stuffed tofu |
—
|
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: Hakka stuffed tofu | Statement: [Hakka cuisine, knownForDish, Hakka stuffed tofu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: knownForDish Context triple: [Hakka cuisine, knownForDish, Hakka stuffed tofu]
-
A.
traditionallyKnownFor
Indicates that something is widely and historically recognized or reputed for a particular characteristic, activity, product, or role.
-
B.
isNationalDishOf
Indicates that a particular food is officially or culturally recognized as the national dish of a specific country or region.
-
C.
servesDish
Indicates that one entity prepares and presents a specific dish as food for another entity.
-
D.
formerlyKnownFor
Indicates that an entity was previously recognized or notable for a particular role, attribute, or activity, but is no longer primarily associated with it.
-
E.
sharesCuisineWith
Indicates that two entities offer or are associated with the same type or style of cuisine.
- F. None of above. chosen
Provenance (4 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_69ca8282ccec819083c48efb72d21cf9 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cafa0c1f5c8190b16db20daad159a1 |
completed | March 30, 2026, 10:32 p.m. |
| PD | Predicate disambiguation | batch_69cae91ae008819098e56bbe51143b31 |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf7855a3c81908b9318f7186fc0c0 |
completed | March 30, 2026, 10:21 p.m. |
Created at: March 30, 2026, 4:42 p.m.