Triple
T28377563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maghaberry |
E718792
|
entity |
| Predicate | prisonSecurityLevel |
P148082
|
FINISHED |
| Object | high security |
—
|
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: high security | Statement: [Maghaberry, prisonSecurityLevel, high security]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: prisonSecurityLevel Context triple: [Maghaberry, prisonSecurityLevel, high security]
-
A.
securityForInmates
Indicates the provision or management of protective measures and safeguards specifically intended for inmates.
-
B.
prisonType
Indicates the specific category or classification of a prison associated with an entity.
-
C.
hasInmateCustodyLevel
Indicates the security or supervision level at which an inmate is held in custody.
-
D.
majorPenitentiary
Indicates that an entity serves as a primary or principal penitentiary (major prison) within a given system or jurisdiction.
-
E.
hasHighSecurityFacility
chosen
Indicates that an entity possesses or operates a facility characterized by a high level of security measures and protections.
- 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_69eff6ee5afc8190bd7375a29f0cc6c6 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64c5eee988190aa18cd909ea3e855 |
completed | May 2, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 1:04 a.m.