Triple
T18065658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IRN-BRU |
E432285
|
entity |
| Predicate | regulatoryChangeImpact |
P44198
|
FINISHED |
| Object | UK sugar tax |
—
|
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: UK sugar tax | Statement: [IRN-BRU, regulatoryChangeImpact, UK sugar tax]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regulatoryChangeImpact Context triple: [IRN-BRU, regulatoryChangeImpact, UK sugar tax]
-
A.
regulationImpact
chosen
Indicates how a regulation influences, constrains, or alters the behavior, performance, or outcomes associated with the related entities.
-
B.
regulationChangeComparedToPrevious
Indicates a change in a regulation relative to its immediately preceding version or state.
-
C.
typeOfChangeRegulated
Indicates that one entity specifies or controls the kind of change or modification that is allowed or governed in another entity or process.
-
D.
safetyRegulationChange
Indicates a modification, update, or revision to existing safety regulations governing how something must be designed, operated, or managed.
-
E.
safetyRegulationEffect
Indicates how a safety regulation influences or changes the conditions, behaviors, or outcomes associated with the regulated entities.
- 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_69d8b9070cac81909fa9473fb1c3f1c7 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4cce81de88190bd94d4ccee3e180c |
completed | April 19, 2026, 12:39 p.m. |
| PD | Predicate disambiguation | batch_69e3f90c652481908133a73106d78919 |
completed | April 18, 2026, 9:35 p.m. |
Created at: April 10, 2026, 10:26 a.m.