Triple
T8211805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maghaberry Prison |
E191834
|
entity |
| Predicate | holdsCategory |
P15481
|
FINISHED |
| Object | Category A equivalent 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: Category A equivalent prisoners | Statement: [Maghaberry Prison, holdsCategory, Category A equivalent prisoners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holdsCategory Context triple: [Maghaberry Prison, holdsCategory, Category A equivalent prisoners]
-
A.
hasCategoryOn
chosen
Indicates that something is assigned to or associated with a specific category within a given context or scope.
-
B.
holdingType
Indicates the type or category of a holding or possession that one entity has in relation to another or to an asset.
-
C.
hasRetailCategory
Indicates that an entity is associated with a specific retail category or type of retail business.
-
D.
containsCategory
Indicates that one entity includes or encompasses a specific category as part of its classification or organizational structure.
-
E.
typicallyHolds
Indicates that a certain relationship or condition generally holds true in typical or normal situations, though not necessarily in all cases.
- 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_69ca82c8c054819087fedd9a5436b8a3 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb76dec42c819090252fe186a68d34 |
completed | March 31, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69cb36ad01ac81909609b15f6a6c8581 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:44 p.m.