Triple
T1659668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vote Leave |
E35875
|
entity |
| Predicate | notableClaim |
P13068
|
FINISHED |
| Object | The UK sends £350 million a week to the EU |
—
|
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: The UK sends £350 million a week to the EU | Statement: [Vote Leave, notableClaim, The UK sends £350 million a week to the EU]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableClaim Context triple: [Vote Leave, notableClaim, The UK sends £350 million a week to the EU]
-
A.
hasNotableClaim
chosen
Indicates that an entity is associated with a significant, widely recognized statement, assertion, or claim.
-
B.
notableFor
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
-
C.
notableFact
Indicates that there exists a particularly significant or noteworthy fact or piece of information associated with the subject.
-
D.
notableDuring
Indicates that something was especially prominent, active, or significant during a particular time period or event.
-
E.
notableSingle
Indicates that the subject is particularly recognized or distinguished for one specific, individual instance (such as a single work, event, or achievement).
- 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_69a88606aa808190aa0b421b4271f220 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaf3359ce48190803b322db8ad6027 |
completed | March 6, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69a907cff53c8190b424f088478d3e2c |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:29 p.m.