Triple
T27742260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2014 South African general election |
E701884
|
entity |
| Predicate | COPEVoteSharePercentage |
P9216
|
FINISHED |
| Object | 0.67 |
—
|
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: 0.67 | Statement: [2014 South African general election, COPEVoteSharePercentage, 0.67]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: COPEVoteSharePercentage Context triple: [2014 South African general election, COPEVoteSharePercentage, 0.67]
-
A.
popularVoteShare
chosen
Indicates the proportion of all votes cast in an election that were received by a particular candidate, party, or option.
-
B.
publicVoteWeight
Indicates that an entity’s influence or impact in a public voting process is quantified by a specific weight or value.
-
C.
voteSplit
Indicates that a voting outcome is divided among multiple options or parties rather than being unanimous or clearly majority.
-
D.
voteRecord
Indicates that an entity has cast a specific vote or holds a particular voting position in a given decision or election.
-
E.
voteResult
Indicates the outcome or decision produced by a voting process involving the related entities.
- 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_69ef6a53c7388190899baa6daf42301c |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f63717b8c48190abd8ebcc54c76c46 |
completed | May 2, 2026, 5:40 p.m. |
| PD | Predicate disambiguation | batch_69f63188e7408190af8ce8b93d128c63 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 4:12 p.m.