Triple
T20071725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1992 United Kingdom general election |
E499753
|
entity |
| Predicate | labourVoteSwingPercentagePoints |
P62221
|
FINISHED |
| Object | +3.6 |
—
|
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: +3.6 | Statement: [1992 United Kingdom general election, labourVoteSwingPercentagePoints, +3.6]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: labourVoteSwingPercentagePoints Context triple: [1992 United Kingdom general election, labourVoteSwingPercentagePoints, +3.6]
-
A.
LabourVoteSwing
Indicates a change in the proportion of votes received by the Labour Party between two elections or time periods.
-
B.
swingToLabourPercentagePoints
chosen
Indicates the change in voter support, measured in percentage points, shifting from another party or baseline to the Labour Party.
-
C.
labourPopularVoteShare
Indicates the proportion of all valid votes cast that were received by the Labour Party in a given election or electoral contest.
-
D.
numberOfVotesLabour
Indicates the total count of votes that were cast for the Labour party in a given election or voting context.
-
E.
party1VoteSwing
Indicates the change in vote share or support experienced by the first party between two electoral contexts or time points.
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66438633481908710907c48806499 |
completed | April 20, 2026, 5:36 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:40 p.m.