Triple
T7845630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Separate Amenities Act |
E181915
|
entity |
| Predicate | privileged |
P20239
|
FINISHED |
| Object | white South Africans |
—
|
LITERAL 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: white South Africans | Statement: [Separate Amenities Act, privileged, white South Africans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: privileged Context triple: [Separate Amenities Act, privileged, white South Africans]
-
A.
elite
chosen
Indicates that the subject belongs to a select, superior, or highly privileged subset within a larger group or category.
-
B.
politicalPrivilege
Indicates that an entity benefits from special advantages, immunities, or favorable treatment within a political system or power structure.
-
C.
exclusivePower
Indicates that one entity holds sole authority or control over another entity or a specific domain, excluding others from sharing that power.
-
D.
favored
Indicates that one entity is preferred, supported, or given advantage over others by another entity.
-
E.
parity
Indicates that two quantities share the same evenness or oddness, or more generally that they have equivalent status or value in a given context.
- 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_69ca8285d6488190a95d4c02d7354b53 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb163d92fc8190a4efcb08d6b3d404 |
completed | March 31, 2026, 12:33 a.m. |
| PD | Predicate disambiguation | batch_69cae92180f88190ae3d44c3de7adc93 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:49 p.m.