Triple
T27766851
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 客家人 |
E701622
|
entity |
| Predicate | 传统饮食 |
P19483
|
FINISHED |
| Object | 盐焗鸡 |
—
|
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: 盐焗鸡 | Statement: [客家人, 传统饮食, 盐焗鸡]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 传统饮食 Context triple: [客家人, 传统饮食, 盐焗鸡]
-
A.
traditionalCuisine
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.
-
B.
traditionalDish
chosen
Indicates that the object is a dish customarily prepared, eaten, or recognized within the subject’s cultural or regional tradition.
-
C.
traditionalFoodBase
Indicates that one entity serves as the primary ingredient, staple, or foundational component of a traditional food associated with another entity.
-
D.
traditionalLifestyle
Indicates that an entity follows or maintains long-established customs, practices, and ways of living, typically in contrast to modern or industrialized lifestyles.
-
E.
foodCulture
Indicates the relationship between a place or group and its characteristic traditions, practices, and preferences surrounding food and eating.
- 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_69ef6a52fa708190934a32308d2c92dc |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f63894e5848190aec428392562ab06 |
completed | May 2, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_69f6370c8c7c8190a02ea82847bb6e76 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 4:31 p.m.