Triple
T5028452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HM Prison Usk |
E113234
|
entity |
| Predicate | primaryInmateType |
P28113
|
FINISHED |
| Object | vulnerable prisoners |
—
|
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: vulnerable prisoners | Statement: [HM Prison Usk, primaryInmateType, vulnerable prisoners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryInmateType Context triple: [HM Prison Usk, primaryInmateType, vulnerable prisoners]
-
A.
prisonType
Indicates the specific category or classification of a prison associated with an entity.
-
B.
inmates
Indicates that one entity is confined or held as a prisoner within an institution or facility associated with another entity.
-
C.
detentionType
Indicates the specific category or form of detention applied to an entity within a custodial or restrictive context.
-
D.
prisonRole
Indicates a role or function that an entity holds within the context or system of a prison.
-
E.
primaryType
chosen
Indicates the main or most fundamental category or classification assigned to an entity, distinguishing it from any secondary or auxiliary types.
- 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_69bd443775e48190a646ffbfc4334723 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd738f2cc88190a03eebf19e407411 |
completed | March 20, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69bd71509e9c8190a60c1d8d04936a12 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:36 p.m.