Triple
T6770091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2011 Welsh devolution referendum |
E155020
|
entity |
| Predicate | yesPercentage |
P38650
|
FINISHED |
| Object | 63.5% |
—
|
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: 63.5% | Statement: [2011 Welsh devolution referendum, yesPercentage, 63.5%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yesPercentage Context triple: [2011 Welsh devolution referendum, yesPercentage, 63.5%]
-
A.
yesVotes
Indicates that a specified entity has cast or received affirmative votes in a decision-making or voting context.
-
B.
supportPercentage
chosen
Indicates the proportion or share of total backing, approval, or assistance that one entity provides to or receives from another, typically expressed as a percentage.
-
C.
approvalRate
Indicates the proportion or percentage of subjects that express approval or a positive evaluation toward a given entity or action.
-
D.
noVotesPercentage
Indicates the proportion of total votes that were cast as "no" in a given decision or election.
-
E.
votePattern
Indicates a recurring way or tendency in how an entity casts votes across issues, candidates, or time.
- 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_69c68812ef7c819099369f51febb725c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2347fb48190a44c03317b5ecfd7 |
completed | March 27, 2026, 6:53 p.m. |
| PD | Predicate disambiguation | batch_69c6d094105881909c5806eb4afa6306 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:13 p.m.