Triple
T9876498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Špilberk Castle |
E240084
|
entity |
| Predicate | prisonFor |
P22043
|
FINISHED |
| Object | political prisoners |
—
|
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: political prisoners | Statement: [Špilberk Castle, prisonFor, political prisoners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: prisonFor Context triple: [Špilberk Castle, prisonFor, political prisoners]
-
A.
imprisonedFor
Indicates that one entity is held in detention or jail as a consequence of, or in connection with, a specific reason, action, or offense committed by another entity or itself.
-
B.
usedForImprisoning
chosen
Indicates that something serves as a means, tool, or method for confining or detaining someone against their will.
-
C.
prisonerOf
Indicates that one entity is held in custody or confinement by another entity, typically under legal or authoritative control.
-
D.
prisonType
Indicates the specific category or classification of a prison associated with an entity.
-
E.
hasPrison
Indicates that one entity possesses, contains, or is the location of a prison associated with another entity.
- 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_69ca84e8a0788190b9061811d50fd554 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3fb58d481908407898912c4b4e9 |
completed | April 2, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69cd1d810ed48190a252b70e9390c8f3 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:37 p.m.