Triple
T274905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brexit |
E5225
|
entity |
| Predicate | referendumResultLeavePercentage |
P8661
|
FINISHED |
| Object | 51.9 |
—
|
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: 51.9 | Statement: [Brexit, referendumResultLeavePercentage, 51.9]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: referendumResultLeavePercentage Context triple: [Brexit, referendumResultLeavePercentage, 51.9]
-
A.
dateOfBrexit
Indicates the specific calendar date on which Brexit (the United Kingdom’s withdrawal from the European Union) formally took place.
-
B.
voterTurnoutPercentage
Indicates the proportion of eligible or registered voters who actually cast a ballot in a given election, expressed as a percentage.
-
C.
wonParliamentaryElection
Indicates that one party or candidate achieved victory in a parliamentary election over others.
-
D.
numberOfSeatsWonIn2019ParliamentaryElection
Indicates the number of seats an entity won in the 2019 parliamentary election.
-
E.
seatsWonIn2019ParliamentaryElection
Indicates the number of seats an entity secured in the 2019 parliamentary election.
- 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_69a257e6c8788190987dfe705ca2912a |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25dd1cdf881909c2c9b77b7f88684 |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b7345c4819086c21710864a1b42 |
completed | Feb. 28, 2026, 3:05 a.m. |
| PDg | Predicate description generation | batch_69a25c036b54819090a101c4cbdbcff7 |
completed | Feb. 28, 2026, 3:07 a.m. |
Created at: Feb. 28, 2026, 2:59 a.m.