Triple
T9501508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holman Correctional Facility |
E229150
|
entity |
| Predicate | typeOfPrison |
P19110
|
FINISHED |
| Object | adult male maximum-security facility |
—
|
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: adult male maximum-security facility | Statement: [Holman Correctional Facility, typeOfPrison, adult male maximum-security facility]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfPrison Context triple: [Holman Correctional Facility, typeOfPrison, adult male maximum-security facility]
-
A.
prisonType
chosen
Indicates the specific category or classification of a prison associated with an entity.
-
B.
prisonName
Indicates that an entity is known by a particular prison’s name.
-
C.
isPenalInstitution
Indicates that an entity functions as a facility where individuals are legally confined as punishment or while awaiting legal proceedings.
-
D.
prisonLocatedIn
Indicates that a prison is situated within or at a specific geographic or administrative location.
-
E.
operatedPrison
Indicates that an entity managed, ran, or was responsible for the day-to-day operation of a particular prison.
- 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_69ca84753660819098e8d416e89e26ae |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd983d4b708190a4dfef1246986a26 |
completed | April 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69cca5651a588190a3cfebe249a223e5 |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 7:57 p.m.