Triple
T2605934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Universal Credit |
E58657
|
entity |
| Predicate | replacesSystem |
P29646
|
FINISHED |
| Object | legacy benefits system |
—
|
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: legacy benefits system | Statement: [Universal Credit, replacesSystem, legacy benefits system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacesSystem Context triple: [Universal Credit, replacesSystem, legacy benefits system]
-
A.
replacedSubsystem
Indicates that one subsystem has been substituted or exchanged for another, taking over its role or function.
-
B.
replacedInSystemVersion
Indicates that one entity has been superseded or substituted by another in a specific version of a system.
-
C.
replacesComponentOf
Indicates that one entity takes the place of a specific component within another entity, substituting for that component in its role or function.
-
D.
replacedSystemUsedUntil
Indicates that one system was used up until it was replaced by another system.
-
E.
replacedWith
chosen
Indicates that one entity has been substituted or superseded by another entity, taking over its role, function, or position.
- 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.