Triple
T20951854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HM Prison Long Lartin |
E515997
|
entity |
| Predicate | typeOfOffendersHeld |
P131160
|
FINISHED |
| Object | long-term 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: long-term prisoners | Statement: [HM Prison Long Lartin, typeOfOffendersHeld, long-term prisoners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfOffendersHeld Context triple: [HM Prison Long Lartin, typeOfOffendersHeld, long-term prisoners]
-
A.
targetOffenderType
Indicates the specific category or type of offender that an action, rule, or condition is directed toward.
-
B.
prisonerType
Indicates the classification or category assigned to a prisoner within a correctional or detention system.
-
C.
detentionType
Indicates the specific category or form of detention applied to an entity within a custodial or restrictive context.
-
D.
primaryPrisonerGroups
chosen
Indicates the main categories or groupings into which prisoners are primarily classified or organized.
-
E.
detentionCentreSubjectOf
Indicates that a detention centre is the primary topic, focus, or subject of a related document, statement, or information resource.
- 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_69e0b4fcd678819087a304291f14330a |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fade4e2c81908ab2619d74fcc5a7 |
completed | April 21, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69e5c9b1bae48190a845165fed1b005e |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 1:26 p.m.