Triple
T2648930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thabo Mbeki |
E53850
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Thabo |
E291262
|
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: Thabo | Statement: [Thabo Mbeki, givenName, Thabo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thabo Context triple: [Thabo Mbeki, givenName, Thabo]
-
A.
Thabo
chosen
Thabo is a common Southern African given name, often used in countries such as South Africa and Lesotho.
-
B.
Thabana Ntlenyana
Thabana Ntlenyana is the highest mountain in southern Africa, located in the Drakensberg range within Lesotho.
-
C.
Zwelibanzi Hlongwane
Zwelibanzi Hlongwane is a South African businessman best known as the former husband of Zindzi Mandela, the daughter of Nelson Mandela.
-
D.
Popo Molefe
Popo Molefe is a South African anti-apartheid activist and politician who played a prominent leadership role in the struggle against apartheid and later in democratic governance.
-
E.
Sabata Dalindyebo
Sabata Dalindyebo was a prominent South African traditional leader and king of the Thembu people who became known for his resistance to apartheid-era policies.
- 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_69ab495e192081909c77b622e8e7e15a |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd91b4b3c81908571e85a1621dfc5 |
completed | March 7, 2026, 7:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afb674ed4c8190a398fccdbd30e9c2 |
completed | March 10, 2026, 6:13 a.m. |
Created at: March 6, 2026, 9:53 p.m.