Triple
T36258875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellsworth Correctional Facility |
E892023
|
entity |
| Predicate | hasMailingRestrictions |
P204129
|
FINISHED |
| Object | regulated inmate mail |
—
|
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: regulated inmate mail | Statement: [Ellsworth Correctional Facility, hasMailingRestrictions, regulated inmate mail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMailingRestrictions Context triple: [Ellsworth Correctional Facility, hasMailingRestrictions, regulated inmate mail]
-
A.
hasMarketingRestrictions
Indicates that there are specific limitations or conditions imposed on how something may be marketed or promoted.
-
B.
hasExportRestriction
Indicates that an entity is subject to limitations or controls on exporting it to other jurisdictions or parties.
-
C.
hasHumanUseRestriction
Indicates that there is a limitation or condition on how something may be used by humans.
-
D.
mayHaveRestriction
Indicates that an entity can be subject to one or more limitations, conditions, or constraints, though such restrictions are not necessarily present.
-
E.
hasCoverageRestriction
Indicates that there is a limitation, exclusion, or condition applied to the scope or extent of coverage provided.
- F. None of above. chosen
Provenance (4 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_69f76e4699188190af045b11a840ce31 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a032b2285ac81908826f311a222c749 |
completed | May 12, 2026, 1:29 p.m. |
| PD | Predicate disambiguation | batch_6a032929b8b88190bf7d14d789b38aeb |
completed | May 12, 2026, 1:20 p.m. |
| PDg | Predicate description generation | batch_6a032b21d5b08190bf4690cbf6c1d3de |
completed | May 12, 2026, 1:29 p.m. |
Created at: May 3, 2026, 4:09 p.m.