Triple
T15341793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2011 United Kingdom Alternative Vote referendum |
E366811
|
entity |
| Predicate | percentageAgainstChange |
P92182
|
FINISHED |
| Object | 67.9 |
—
|
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: 67.9 | Statement: [2011 United Kingdom Alternative Vote referendum, percentageAgainstChange, 67.9]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: percentageAgainstChange Context triple: [2011 United Kingdom Alternative Vote referendum, percentageAgainstChange, 67.9]
-
A.
percentage
chosen
Indicates the proportion or share of one quantity relative to another, typically expressed as a value out of 100.
-
B.
priceChange
Indicates a change in the price of an entity, typically specifying how much and/or in what direction the price has moved over a given period.
-
C.
previousRatio
Indicates the proportional relationship between two quantities as they existed in a prior or earlier state or time period.
-
D.
percentageMainOpponent
Indicates the proportion, expressed as a percentage, that a main opponent represents relative to a defined total or context.
-
E.
goalPercentage
Indicates the proportion of a goal that has been achieved relative to its total target.
- 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_69d85a1355608190a6673ddb67231d54 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e14d8088190876fceca75d12322 |
completed | April 16, 2026, 1:40 a.m. |
| PD | Predicate disambiguation | batch_69deca991e5081908b0df3d1ee7d5338 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:17 a.m.