Triple
T1126589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tshivenda |
E24733
|
entity |
| Predicate | ethnicGroup |
P194
|
FINISHED |
| Object | Venda people |
E52951
|
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: Venda people | Statement: [Tshivenda, ethnicGroup, Venda people]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Venda people Context triple: [Tshivenda, ethnicGroup, Venda people]
-
A.
Venda
chosen
Venda is a Bantu language of the Venda people of South Africa and Zimbabwe, recognized as one of South Africa’s official languages.
-
B.
Sellin
Sellin is a seaside resort town on the German island of Rügen, known for its historic pier and Baltic Sea beaches.
-
C.
Mishing people
The Mishing people are an indigenous Tibeto-Burman–speaking community of the Brahmaputra Valley known for their riverine settlements, agriculture, and rich folk music and dance traditions.
-
D.
Damara people
The Damara people are an indigenous ethnic group of Namibia known for their distinct Khoe language, rich oral traditions, and historical role as pastoralists and miners in the region.
-
E.
Ha people
The Ha people are a Bantu-speaking ethnic group of the African Great Lakes region, primarily inhabiting western Tanzania and parts of neighboring countries, known for their rich agricultural traditions and distinctive cultural practices.
- 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_69a4940712c88190aa244f3fc6070a65 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bbdc2718819094f5519ffb56993b |
completed | March 1, 2026, 10:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac539fc3708190b0b3dec5d5c73a71 |
completed | March 7, 2026, 4:34 p.m. |
Created at: March 1, 2026, 7:44 p.m.