Triple
T722074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Werl Prison |
E14637
|
entity |
| Predicate | hasTypeOfManagement |
P18551
|
FINISHED |
| Object | state-run prison |
—
|
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: state-run prison | Statement: [Werl Prison, hasTypeOfManagement, state-run prison]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfManagement Context triple: [Werl Prison, hasTypeOfManagement, state-run prison]
-
A.
hasTypeOfOrganization
Indicates that an entity is classified as belonging to a particular type or category of organization.
-
B.
hasManagementPlan
Indicates that an entity is associated with a defined management plan specifying how it should be overseen, maintained, or administered.
-
C.
ownsOrManages
Indicates that one entity has ownership of, or managerial control over, another entity.
-
D.
organizationTypeGoverned
Indicates that one entity governs or has authoritative control over a specific type or category of organization.
-
E.
hasCapitalType
Indicates that a specified location’s capital is of a particular type (e.g., political, administrative, or economic capital).
- 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_69a4934c753c81909b309027e48b9b3a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a591124c8190842e7ef18b064198 |
completed | March 1, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69a4a4f513608190b716b939d574c292 |
completed | March 1, 2026, 8:43 p.m. |
| PDg | Predicate description generation | batch_69a4a57267c481909790a1fda3fced08 |
completed | March 1, 2026, 8:45 p.m. |
Created at: March 1, 2026, 7:37 p.m.