Triple
T1645615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African general election, 1994 |
E35574
|
entity |
| Predicate | IFPVoteShare |
P9216
|
FINISHED |
| Object | approximately 10.5 percent |
—
|
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: approximately 10.5 percent | Statement: [South African general election, 1994, IFPVoteShare, approximately 10.5 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: IFPVoteShare Context triple: [South African general election, 1994, IFPVoteShare, approximately 10.5 percent]
-
A.
popularVoteShare
chosen
Indicates the proportion of all votes cast in an election that were received by a particular candidate, party, or option.
-
B.
popularVoteShareThird
Indicates the proportion of total popular votes received by the third-place candidate or option in an election.
-
C.
voteSplit
Indicates that a voting outcome is divided among multiple options or parties rather than being unanimous or clearly majority.
-
D.
votingBasis
Indicates the principle, criterion, or grounds on which a vote or voting decision is made.
-
E.
smithPopularVotePercentage
Indicates the percentage of the popular vote that was received by the entity named Smith in a given election or voting 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_69a88604618c81908b41f6429c431eb6 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a919306fd48190a245fc95e0e759d9 |
completed | March 5, 2026, 5:48 a.m. |
| PD | Predicate disambiguation | batch_69a907cc9d348190b76b0d3f596e5a81 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.