Triple
T2605937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Universal Credit |
E58657
|
entity |
| Predicate | sanctionMechanism |
P18137
|
FINISHED |
| Object | reduction of payment for non-compliance |
—
|
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: reduction of payment for non-compliance | Statement: [Universal Credit, sanctionMechanism, reduction of payment for non-compliance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sanctionMechanism Context triple: [Universal Credit, sanctionMechanism, reduction of payment for non-compliance]
-
A.
sanction
Indicates the imposition of an official penalty or restrictive measure by an authority in response to certain actions or behaviors.
-
B.
typeOfSanction
chosen
Indicates the specific category or kind of sanction that is applied in a given situation.
-
C.
receivedSanctionFrom
Indicates that one entity has been subjected to a formal penalty, restriction, or disciplinary measure imposed by another entity.
-
D.
canImposeSanctions
Indicates that one entity has the authority or power to apply punitive or restrictive measures (sanctions) against another entity.
-
E.
typeOfJusticeMechanism
Indicates the kind or category of justice mechanism that characterizes how justice is pursued or administered in a given context.
- 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_69ab4ac3523881909679750c9f8c2dec |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd8def9bc8190b2e013abffc7b191 |
completed | March 7, 2026, 7:50 a.m. |
| PD | Predicate disambiguation | batch_69abd80ab7248190ba06ba14fe4c5638 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:49 p.m.