Triple
T1187787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Bantu |
E25286
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Bantu language branch |
C3817
|
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: Bantu language branch Context triple: [Southern Bantu, instanceOf, Bantu language branch]
-
A.
Bantu language
chosen
A Bantu language is a member of a large branch of the Niger-Congo language family, spoken primarily in central, eastern, and southern Africa, characterized by noun class systems and agglutinative morphology.
-
B.
Chadic language
A Chadic language is any member of a branch of the Afroasiatic language family spoken primarily in parts of Nigeria, Niger, Chad, Cameroon, and neighboring regions, characterized by diverse phonological systems and complex verb morphology.
-
C.
Dravidian language
A Dravidian language is a member of a family of primarily South Indian and Sri Lankan languages, such as Tamil, Telugu, Kannada, and Malayalam, that share common historical origins and structural features distinct from Indo-European languages.
-
D.
Malayo-Polynesian language
A Malayo-Polynesian language is a member of a large branch of the Austronesian language family spoken across Southeast Asia, Madagascar, and the Pacific islands, characterized by shared phonological, grammatical, and lexical features.
-
E.
Uto-Aztecan language branch
The Uto-Aztecan language branch is a family of Indigenous languages spread from the western United States through northern and central Mexico, including well-known languages such as Nahuatl, Hopi, and Ute.
- F. None of above.
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_69a49427d98881908646d6c63b8cea1e |
completed | March 1, 2026, 7:31 p.m. |
Created at: March 1, 2026, 7:45 p.m.