Triple
T10298677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mamelodi |
E241565
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object | Southern Ndebele |
E26699
|
NE 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: Southern Ndebele | Statement: [Mamelodi, hasLanguage, Southern Ndebele]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Southern Ndebele Context triple: [Mamelodi, hasLanguage, Southern Ndebele]
-
A.
Southern Ndebele
chosen
Southern Ndebele is a Bantu language spoken primarily in South Africa, known for its distinctive click sounds and cultural association with the Ndebele people.
-
B.
Northern Ndebele
Northern Ndebele is a Bantu language of the Nguni group spoken primarily in southwestern Zimbabwe and closely related to Zulu.
-
C.
Southwest Bantu
Southwest Bantu is a subgroup of the Bantu language family comprising closely related languages spoken primarily in southwestern Africa.
-
D.
Northwest Bantu
Northwest Bantu is a subgroup of Bantu languages spoken in parts of Central and West-Central Africa, encompassing languages such as Fang.
-
E.
Sotho
Sotho is a Bantu language of Southern Africa, primarily spoken in Lesotho and South Africa, where it serves as one of the country’s official languages.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2ed50908190962f0d6d049fb964 |
completed | April 7, 2026, 9:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71d35d5908190bb87100c81f2948a |
completed | April 9, 2026, 3:29 a.m. |
Created at: April 6, 2026, 11:44 a.m.