Triple
T25517839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2021 Madrilenian regional election |
E639557
|
entity |
| Predicate | ppVoteSwing |
P158854
|
FINISHED |
| Object | +22.39 percentage points |
—
|
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: +22.39 percentage points | Statement: [2021 Madrilenian regional election, ppVoteSwing, +22.39 percentage points]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ppVoteSwing Context triple: [2021 Madrilenian regional election, ppVoteSwing, +22.39 percentage points]
-
A.
party2VoteSwing
Indicates the change in vote share over time for the second political party relative to a previous election or baseline.
-
B.
party1VoteSwing
Indicates the change in vote share or support experienced by the first party between two electoral contexts or time points.
-
C.
DemocraticPopularVoteSwing
Indicates the change in the share of the popular vote received by the Democratic Party between two elections or time periods.
-
D.
AllianceVoteSwing
Indicates a change in voting support or vote share for a political alliance between two points in time or relative to another benchmark.
-
E.
popularVotes
Indicates the number of votes an entity (such as a candidate or option) receives directly from individual voters in an election or decision process.
- F. None of above. chosen
Provenance (4 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_69e75dbe32e48190a62d749a0ff2a96a |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f8339a8081908738ba23158091c9 |
completed | May 2, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69f480789be08190ab252a6de3797200 |
completed | May 1, 2026, 10:29 a.m. |
| PDg | Predicate description generation | batch_69f48b9058d081908ec9af261ee092e2 |
completed | May 1, 2026, 11:16 a.m. |
Created at: April 21, 2026, 2:57 p.m.