Triple
T12669415
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leleti Khumalo |
E302635
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Leleti |
E302635
|
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: Leleti | Statement: [Leleti Khumalo, givenName, Leleti]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leleti Context triple: [Leleti Khumalo, givenName, Leleti]
-
A.
Leleti Khumalo
chosen
Leleti Khumalo is a South African actress best known for her powerful role in the anti-apartheid film and stage musical "Sarafina!" and for her work in television dramas.
-
B.
Leilani Sarelle
Leilani Sarelle is an American actress best known for her role as Roxy in the 1992 thriller film "Basic Instinct."
-
C.
Megalyn Echikunwoke
Megalyn Echikunwoke is an American actress known for her work in film and television, including roles in series like "CSI: Miami," "Arrow," and "The 4400."
-
D.
Charlize
Charlize is a feminine given name, most famously borne by South African–born actress and producer Charlize Theron.
-
E.
Yaya DaCosta
Yaya DaCosta is an American actress and model known for her work in film, television, and fashion, including roles in "America's Next Top Model," "The Butler," and "Chicago Med."
- 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_69d7bded71a88190bb76e2413af9ea66 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96183a6048190b2ef219eb9d20aa4 |
completed | April 10, 2026, 8:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6719fb8bc8190b581a7fcfb252404 |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:20 p.m.