Triple
T23285285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 泰州 |
E588968
|
entity |
| Predicate | 传统美食 |
P1016
|
FINISHED |
| Object | 泰州早茶 |
—
|
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: 泰州早茶 | Statement: [泰州, 传统美食, 泰州早茶]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 传统美食 Context triple: [泰州, 传统美食, 泰州早茶]
-
A.
traditionalDish
Indicates that the object is a dish customarily prepared, eaten, or recognized within the subject’s cultural or regional tradition.
-
B.
traditionalCuisine
chosen
Indicates that an entity is associated with the customary or historically rooted style of cooking and food preparation characteristic of a particular culture, region, or community.
-
C.
traditionalFoodBase
Indicates that one entity serves as the primary ingredient, staple, or foundational component of a traditional food associated with another entity.
-
D.
foodCulture
Indicates the relationship between a place or group and its characteristic traditions, practices, and preferences surrounding food and eating.
-
E.
feastTraditionalName
Indicates the traditional or customary name by which a particular feast or celebration is known.
- 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_69e25d16e2c08190a291de254703129e |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1964600888190b40ecbefdc8aec64 |
completed | April 29, 2026, 5:25 a.m. |
| PD | Predicate disambiguation | batch_69effcecabd88190856fb6e1d993e4dd |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:59 p.m.