Triple
T37097142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vhavenda |
E918592
|
entity |
| Predicate | homelandDuringApartheid |
P69494
|
FINISHED |
| Object | Venda bantustan |
—
|
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: Venda bantustan | Statement: [Vhavenda, homelandDuringApartheid, Venda bantustan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homelandDuringApartheid Context triple: [Vhavenda, homelandDuringApartheid, Venda bantustan]
-
A.
apartheidEraHomeland
chosen
Indicates that an entity is designated as a homeland territory created or administered under South Africa’s apartheid-era system of racial segregation and governance.
-
B.
legalStatusUnderApartheid
Indicates the legal classification or rights a person or group held under apartheid-era laws and policies.
-
C.
functionDuringApartheid
Indicates that the function, role, or activity occurred specifically during the historical period of apartheid.
-
D.
positionOnApartheid
Indicates a stance, opinion, or policy that an entity holds regarding apartheid.
-
E.
legalStatusDuringApartheid
Indicates the legal classification or rights a person or group held under the laws and policies of the apartheid system.
- F. None of above.
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_69f76e9a48bc8190a3947508d8bca408 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb344c60f8819090f2e21e1e61d621 |
completed | May 6, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69fb2f642db08190b562725502c74ea6 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:14 p.m.