Triple
T1605032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African Party |
E34481
|
entity |
| Predicate | policyOnRace |
P19420
|
FINISHED |
| Object | maintenance of white political dominance |
—
|
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: maintenance of white political dominance | Statement: [South African Party, policyOnRace, maintenance of white political dominance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policyOnRace Context triple: [South African Party, policyOnRace, maintenance of white political dominance]
-
A.
racePolicy
Indicates that an entity has established rules, practices, or guidelines governing how races or competitive events are conducted or managed.
-
B.
peacePolicy
Indicates a policy or set of measures aimed at promoting, maintaining, or restoring peaceful relations between parties.
-
C.
stanceOnSegregation
chosen
Indicates a person or group’s expressed position, attitude, or viewpoint regarding racial or social segregation.
-
D.
policyFocus
Indicates that an entity (such as a person, organization, or document) is primarily concerned with, directed toward, or centered on a particular policy area or issue.
-
E.
policyName
Indicates the specific name or title assigned to a policy associated with an entity.
- 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_69a885fea6a481909fe83ba6441f1774 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93fa6926081908bc78d15c0be3185 |
completed | March 5, 2026, 8:32 a.m. |
| PD | Predicate disambiguation | batch_69a907c35f848190a2428c52e81d013e |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.