Triple
T26815487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Republican Revolution |
E672111
|
entity |
| Predicate | voterTrend |
P41291
|
FINISHED |
| Object | national swing toward Republican candidates |
—
|
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: national swing toward Republican candidates | Statement: [Republican Revolution, voterTrend, national swing toward Republican candidates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: voterTrend Context triple: [Republican Revolution, voterTrend, national swing toward Republican candidates]
-
A.
currentPoliticalTrend
chosen
Indicates the prevailing direction or pattern of political attitudes, behaviors, or power dynamics at a given time.
-
B.
typicalVoters
Indicates that the subject entity is a representative or characteristic member of the group of voters associated with the object entity.
-
C.
voterTurnoutChange
Indicates the amount or direction of change in voter turnout between two elections or time periods.
-
D.
ukipVoteShareChange
Indicates the change in the proportion of votes received by UKIP between two elections or time periods.
-
E.
hasVoterRegistrationTendency
Indicates a tendency or likelihood for an entity to register (or be registered) as a voter.
- 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_69eeb3225a3c8190aaf6746efeded2f3 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61a849f4481908de0e3bc4f61da1c |
completed | May 2, 2026, 3:38 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 4:32 a.m.