Triple
T23060103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Takituduh dialect |
E574273
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | variety of the Bunun language |
C47191
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: variety of the Bunun language Context triple: [Takituduh dialect, instanceOf, variety of the Bunun language]
-
A.
variety of the Guna language
A variety of the Guna language is a distinct regional or social form of Guna characterized by systematic differences in pronunciation, vocabulary, and grammar while remaining mutually intelligible with other Guna forms.
-
B.
variety of Kunama language
A variety of Kunama language is a distinct regional or social form of the Kunama language characterized by unique phonological, lexical, or grammatical features within the broader Kunama-speaking community.
-
C.
variety of the Zhuang language
A variety of the Zhuang language is a distinct regional or social form of Zhuang characterized by its own phonological, lexical, and grammatical features while remaining mutually intelligible to varying degrees with other Zhuang varieties.
-
D.
variety of the Berom language
A variety of the Berom language is a distinct regional or social form of Berom characterized by systematic differences in pronunciation, vocabulary, or grammar while remaining mutually intelligible with other forms.
-
E.
Zhuang language variety
A Zhuang language variety is a specific regional or social form of the Zhuang language, characterized by distinct phonological, lexical, and grammatical features within the broader Tai language continuum.
- F. None of above. chosen
Provenance (1 batch)
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_69e245ba7ae48190be606dbc54120e39 |
completed | April 17, 2026, 2:37 p.m. |
Created at: April 17, 2026, 3:55 p.m.