Triple
T21630206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African Broadcasting Corporation |
E533809
|
entity |
| Predicate | languageOfBroadcast |
P3314
|
FINISHED |
| Object | Tsonga |
—
|
NE NERFINISHED |
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: Tsonga | Statement: [South African Broadcasting Corporation, languageOfBroadcast, Tsonga]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tsonga Context triple: [South African Broadcasting Corporation, languageOfBroadcast, Tsonga]
-
A.
Tsonga
chosen
Tsonga is a Bantu language spoken primarily in southern Africa, especially in Mozambique and South Africa, by the Tsonga (Xitsonga) people.
-
B.
Marakwet
Marakwet is a Southern Nilotic language spoken primarily by the Marakwet people of Kenya’s Rift Valley region.
-
C.
Tchambri
Tchambri is an indigenous people of Papua New Guinea known for their distinctive social organization and for being the focus of anthropological studies by Margaret Mead.
-
D.
Mengoni
Mengoni is an Italian surname most notably associated with figures such as architect Giuseppe Mengoni and contemporary singer Marco Mengoni.
-
E.
Wedza
Wedza is a rural district and township in northeastern Zimbabwe known for its agriculture and gold deposits.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c464fba881908d0ff2ac80511ce1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef521679fc81909c94d42439fda4ba |
completed | April 27, 2026, 12:09 p.m. |
Created at: April 16, 2026, 6:34 p.m.