Triple
T36338020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kober Prison |
E894838
|
entity |
| Predicate | hasHeldPrisonersFrom |
P57303
|
FINISHED |
| Object | Omar al-Bashir regime |
—
|
NE NERFINISHED |
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: Omar al-Bashir regime | Statement: [Kober Prison, hasHeldPrisonersFrom, Omar al-Bashir regime]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHeldPrisonersFrom Context triple: [Kober Prison, hasHeldPrisonersFrom, Omar al-Bashir regime]
-
A.
hasPrisoners
chosen
Indicates that an entity holds or contains one or more individuals who are imprisoned or detained.
-
B.
hasBeenImprisonedBy
Indicates that one entity has been confined or incarcerated under the authority or control of another entity.
-
C.
wasImprisonedIn
Indicates that an entity was held in confinement or incarcerated at a particular place or facility.
-
D.
hasBeenImprisoned
Indicates that an entity has been confined or incarcerated in a prison or similar detention facility at some point in time.
-
E.
detainedPrisonersFrom
Indicates that an authority is holding prisoners who originate from or are associated with a specified place or source.
- 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_69f76e4e90148190b02fe52593c70b5b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fdd07a34c08190982b8c61c2775cf6 |
completed | May 8, 2026, noon |
| PD | Predicate disambiguation | batch_69fdbd25c7908190b72fca8de7ce503f |
completed | May 8, 2026, 10:38 a.m. |
Created at: May 3, 2026, 4:09 p.m.