Triple
T1660418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Single Transferable Vote |
E35891
|
entity |
| Predicate | usesBallotType |
P2726
|
FINISHED |
| Object | ranked ballot |
—
|
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: ranked ballot | Statement: [Single Transferable Vote, usesBallotType, ranked ballot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesBallotType Context triple: [Single Transferable Vote, usesBallotType, ranked ballot]
-
A.
voteType
Indicates the specific category or kind of vote associated with an action or decision (e.g., upvote, downvote, approval, rejection).
-
B.
appliesToElectionType
Indicates that a rule, condition, or attribute is relevant or applicable to a specific type or category of election.
-
C.
votingBasis
Indicates the principle, criterion, or grounds on which a vote or voting decision is made.
-
D.
hasElectionType
Indicates the specific category or kind of election associated with a given electoral event or process.
-
E.
votingMethod
chosen
Indicates the procedure or system by which a vote is cast, collected, and counted in a decision-making or electoral process.
- 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_69a88606aa808190aa0b421b4271f220 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa994f92b0819084ee2f6a672334b9 |
completed | March 6, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69a907d2475c8190b7ec7dccd3335eb1 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:29 p.m.