Triple
T27542023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 客家话 |
E695260
|
entity |
| Predicate | 语系特征 |
P6520
|
FINISHED |
| Object | 保留较多古汉语成分 |
—
|
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: 保留较多古汉语成分 | Statement: [客家话, 语系特征, 保留较多古汉语成分]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 语系特征 Context triple: [客家话, 语系特征, 保留较多古汉语成分]
-
A.
linguisticFeature
chosen
Indicates a relationship where a linguistic property, pattern, or characteristic is attributed to or associated with a language-related entity (such as a word, phrase, or text).
-
B.
linguisticClassificationBasis
Indicates the criterion or principle used as the basis for classifying something within a linguistic system or framework.
-
C.
linguisticClassification
Indicates the relationship by which an entity is categorized according to its language or linguistic type.
-
D.
宗派言語
Indicates a relationship where a particular language is used or associated as the doctrinal or liturgical language of a specific religious sect or denomination.
-
E.
hasLinguisticAreaFeature
Indicates that a linguistic area possesses or is characterized by a particular linguistic feature or property.
- 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_69ef5386c3e08190bfe33aa326e1f72b |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62f5ec8b481909241271f7d602dc9 |
completed | May 2, 2026, 5:07 p.m. |
| PD | Predicate disambiguation | batch_69f623ac3a9c8190a6ee0c137b09e4b0 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 1:31 p.m.