Triple
T25924945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kande language |
E653275
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Tswa–Ronga language variety |
C50094
|
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: Tswa–Ronga language variety Context triple: [Kande language, instanceOf, Tswa–Ronga language variety]
-
A.
Makhuwa language variety
A Makhuwa language variety is a specific regional or social form of the Makhuwa Bantu language, distinguished by its own phonological, lexical, or grammatical features within the broader Makhuwa linguistic continuum.
-
B.
Central Khoisan language
A Central Khoisan language is a member of the Khoisan language family spoken primarily in central southern Africa, characterized by extensive use of click consonants and complex phonological systems.
-
C.
Sabaki language
Sabaki language is a conceptual class representing a subgroup of closely related Bantu languages spoken along the East African coast, characterized by shared phonological, lexical, and grammatical features.
-
D.
Grassfields language
A Grassfields language is a member of a subgroup of Southern Bantoid languages spoken primarily in the Grassfields region of western Cameroon, characterized by complex noun class systems and tonal distinctions.
-
E.
Ubangian language
A Ubangian language is a member of a proposed group of Central African languages, primarily spoken in the Central African Republic and neighboring countries, that share common phonological and grammatical features and are often considered a branch of the Niger-Congo family.
- 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_69e7ab3eb9b881909c1390690551f868 |
completed | April 21, 2026, 4:52 p.m. |
Created at: April 22, 2026, 8:35 a.m.