Triple
T12966621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mbongeni Ngema |
E321277
|
entity |
| Predicate | wrote |
P2831
|
FINISHED |
| Object | Asinamali! |
E1013524
|
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: Asinamali! | Statement: [Mbongeni Ngema, wrote, Asinamali!]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asinamali! Context triple: [Mbongeni Ngema, wrote, Asinamali!]
-
A.
Asinamali!
chosen
Asinamali! is a renowned South African anti-apartheid stage musical and play created by Mbongeni Ngema that dramatizes the struggles of black South Africans under apartheid.
-
B.
Asimjeeg
Asimjeeg is a dialect of the Datooga language spoken by a subgroup of the Datooga people in Tanzania.
-
C.
Asikkala
Asikkala is a municipality in southern Finland known for its lakeside landscapes and location within the Päijät-Häme region.
-
D.
Asake
Asake is a Nigerian singer and songwriter known for his energetic fusion of Afrobeats, amapiano, and street-pop, and for being one of the standout artists on Olamide’s YBNL Nation label.
-
E.
Asmal
Asmal is a surname most notably associated with Kader Asmal, a prominent South African anti-apartheid activist, academic, and government minister.
- 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_69d80763bd6c819094437da5b20b01d2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e3f702481908f0f90f4f12d3f4d |
completed | April 10, 2026, 10:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6c0f4798c8190861638c699e98045 |
completed | May 3, 2026, 3:28 a.m. |
Created at: April 9, 2026, 8:30 p.m.