Triple
T12966622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mbongeni Ngema |
E321277
|
entity |
| Predicate | wrote |
P2831
|
FINISHED |
| Object | Township Fever |
E1013184
|
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: Township Fever | Statement: [Mbongeni Ngema, wrote, Township Fever]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Township Fever Context triple: [Mbongeni Ngema, wrote, Township Fever]
-
A.
Township Fever
chosen
Township Fever is a South African musical theatre production by Mbongeni Ngema that portrays the struggles and resilience of black communities under apartheid.
-
B.
Hillbilly Fever
"Hillbilly Fever" is a country/bluegrass song by The Osborne Brothers that showcases their high-energy vocal harmonies and traditional Appalachian sound.
-
C.
Red Town
Red Town is a historical region associated with the settlement of Krasnaya Sloboda, known for its cultural and regional significance.
-
D.
Sugar Town
"Sugar Town" is a 1966 pop song by Nancy Sinatra, known for its light, whimsical style and catchy, laid-back melody.
-
E.
Goin' to Town
"Goin' to Town" is a 1935 American comedy film starring Mae West, known for its witty dialogue and West's trademark bold, comedic persona.
- 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.