Triple
T19713399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgia State Prison |
E473411
|
entity |
| Predicate | typeOfOffendersHoused |
P131305
|
FINISHED |
| Object | violent offenders |
—
|
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: violent offenders | Statement: [Georgia State Prison, typeOfOffendersHoused, violent offenders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfOffendersHoused Context triple: [Georgia State Prison, typeOfOffendersHoused, violent offenders]
-
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.
prisonType
Indicates the specific category or classification of a prison associated with an entity.
-
D.
primaryPrisonerGroups
Indicates the main categories or groupings into which prisoners are primarily classified or organized.
-
E.
primaryIncarceratedGroup
chosen
Indicates that the referenced group is the main or predominant population being held in incarceration within a given facility, system, or context.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6440a0f2c8190803ace7f6b4ed6e9 |
completed | April 20, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69e530438c60819082364c7be3eef6f0 |
completed | April 19, 2026, 7:42 p.m. |
Created at: April 10, 2026, 1:46 p.m.