Triple
T219399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welsh Government |
E4179
|
entity |
| Predicate | canRaise |
P8210
|
FINISHED |
| Object | devolved Welsh taxes |
—
|
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: devolved Welsh taxes | Statement: [Welsh Government, canRaise, devolved Welsh taxes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canRaise Context triple: [Welsh Government, canRaise, devolved Welsh taxes]
-
A.
canMake
Indicates that one entity has the ability or capacity to create, produce, or assemble another entity.
-
B.
canBe
Indicates that one entity has the potential, permission, or capability to become, perform as, or be classified as another entity.
-
C.
canReport
Indicates that one entity has the ability or permission to report on, or submit a report about, another entity or situation.
-
D.
canEnforce
Indicates that one entity has the authority or capability to compel compliance with rules, decisions, or obligations upon another entity.
-
E.
canSet
Indicates that one entity has the ability or permission to assign, configure, or change a property, value, or state of another entity.
- 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_69a2573508588190b522c2476d91acfe |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25c6d0fa08190810139b14f4851bc |
completed | Feb. 28, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69a25b5357bc8190b29a48e3053fb76d |
completed | Feb. 28, 2026, 3:04 a.m. |
| PDg | Predicate description generation | batch_69a25be349588190aedde33d80682344 |
completed | Feb. 28, 2026, 3:07 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.