Triple
T27968298
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 畲族 |
E704784
|
entity |
| Predicate | 与其他民族关系 |
P123076
|
FINISHED |
| Object | 与客家人文化联系密切 |
—
|
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: 与客家人文化联系密切 | Statement: [畲族, 与其他民族关系, 与客家人文化联系密切]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 与其他民族关系 Context triple: [畲族, 与其他民族关系, 与客家人文化联系密切]
-
A.
interethnicRelations
chosen
Indicates the nature and dynamics of interactions, relationships, and attitudes between different ethnic groups.
-
B.
isPartOfCrossStraitRelations
Indicates that something belongs to, affects, or is involved in the political, economic, social, or cultural interactions and dynamics between the two sides of the Taiwan Strait.
-
C.
otherEthnicGroup
Indicates that one entity belongs to a different ethnic group than the other entity.
-
D.
関連国境
Indicates a relationship where something is associated with, concerns, or pertains to a national border.
-
E.
hasCulturalRelation
Indicates a relationship in which entities are connected through shared, influencing, or interacting cultural practices, values, traditions, or expressions.
- 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_69ef841061e48190b5570f9562f7434d |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f63fd79e4c8190af9263b679e5ff07 |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6895f0819088655277e45859a8 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 7:36 p.m.