Triple
T27932319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African general election, 1981 |
E708014
|
entity |
| Predicate | excludedGroups |
P3119
|
FINISHED |
| Object | Black 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: Black South Africans | Statement: [South African general election, 1981, excludedGroups, Black South Africans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: excludedGroups Context triple: [South African general election, 1981, excludedGroups, Black South Africans]
-
A.
excludedFrom
Indicates that one entity is deliberately not included within the scope, membership, or applicability of another entity or set.
-
B.
isExcludedFor
Indicates that a particular entity is not allowed, applicable, or considered within a specified context, condition, or set.
-
C.
excludes
chosen
Indicates that one entity deliberately omits, leaves out, or does not allow the inclusion of another entity within a set, group, or context.
-
D.
excludesMode
Indicates that one mode, option, or operational state is defined as incompatible with and therefore prevents the use of another mode.
-
E.
excludesConstruct
Indicates that one entity explicitly omits, leaves out, or does not incorporate a particular construct in its definition, composition, or scope.
- 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_69ef96bbf2c48190a9d0e0291457aab6 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c2f81c8190bf369226306eef09 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 27, 2026, 7:03 p.m.