Triple
T27766863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 客家人 |
E701622
|
entity |
| Predicate | 语言特征 |
P24616
|
FINISHED |
| Object | 保留较多中古汉语成分 |
—
|
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: 保留较多中古汉语成分 | Statement: [客家人, 语言特征, 保留较多中古汉语成分]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 语言特征 Context triple: [客家人, 语言特征, 保留较多中古汉语成分]
-
A.
linguisticFeature
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.
languageCharacterizedBy
chosen
Indicates that a language is defined or distinguished by a particular feature, property, or characteristic.
-
C.
linguisticFeatureStatus
Indicates the current condition or state of a particular linguistic feature (such as whether it is present, active, obsolete, or otherwise characterized) in relation to an entity.
-
D.
writingSystemFeatures
Indicates the specific structural or functional characteristics that define how a particular writing system represents language.
-
E.
languageTrait
Indicates that an entity possesses a specific characteristic, feature, or quality related to language.
- 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_69f637939be0819082653d4115cd1be1 |
completed | May 2, 2026, 5:42 p.m. |
| PD | Predicate disambiguation | batch_69f63188e7408190af8ce8b93d128c63 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 4:31 p.m.