Triple
T8004724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African Constitution of 1983 |
E186335
|
entity |
| Predicate | referendumHeldAmong |
P80277
|
FINISHED |
| Object | white voters only |
—
|
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 voters only | Statement: [South African Constitution of 1983, referendumHeldAmong, white voters only]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: referendumHeldAmong Context triple: [South African Constitution of 1983, referendumHeldAmong, white voters only]
-
A.
heldReferendum
Indicates that an entity organized and conducted a referendum, typically allowing eligible participants to vote directly on a specific issue or proposal.
-
B.
referendumRelated
Indicates a relationship where something is connected to, associated with, or arising from a referendum process or its outcomes.
-
C.
referendumResult
Indicates the outcome or decision reached by voters in a specific referendum.
-
D.
subjectOfReferendum
Indicates that something is the issue, proposal, or matter being decided upon in a referendum.
-
E.
referendumYesPercentage
Indicates the percentage of votes cast in favor of the "yes" option in a referendum.
- F. None of above. chosen
Provenance (4 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_69ca82aaaf24819084b94d18f699ba53 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3cf5fb588190ada4ec7d8087619c |
completed | March 31, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69cb048c9f488190b4fb8917a9c21bc5 |
completed | March 30, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69cb14bbbacc81909c6cf8ec35314bbb |
completed | March 31, 2026, 12:26 a.m. |
Created at: March 30, 2026, 5:18 p.m.