Triple
T21969669
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zolani Mahola |
E542553
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Zolani Mahola |
—
|
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: Zolani Mahola | Statement: [Zolani Mahola, name, Zolani Mahola]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zolani Mahola Context triple: [Zolani Mahola, name, Zolani Mahola]
-
A.
Zolani Mahola
chosen
Zolani Mahola is a South African singer, actress, and storyteller best known as the charismatic lead vocalist of the Afro-fusion band Freshlyground.
-
B.
Adam Zindani
Adam Zindani is a British musician best known as the guitarist for the rock band Stereophonics.
-
C.
Velile Tshabalala
Velile Tshabalala is a British actress best known to Doctor Who fans for her role in the 2008 Christmas special "The Next Doctor."
-
D.
Sandile Zungu
Sandile Zungu is a South African businessman and sports executive best known for owning and leading the Premier Soccer League club AmaZulu FC.
-
E.
Sam Nhlengethwa
Sam Nhlengethwa is a prominent South African artist known for his collage-based works that explore jazz culture, township life, and social realities.
- 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_69e0c48070988190909db97667b9a0ac |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1245e4ebc8190968108cc95a22fe4 |
completed | April 28, 2026, 9:19 p.m. |
Created at: April 16, 2026, 8:02 p.m.