Triple
T31952955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Detention Site Black |
E815829
|
entity |
| Predicate | transportedDetaineesFrom |
P13731
|
FINISHED |
| Object | various CIA black sites |
—
|
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: various CIA black sites | Statement: [Detention Site Black, transportedDetaineesFrom, various CIA black sites]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transportedDetaineesFrom Context triple: [Detention Site Black, transportedDetaineesFrom, various CIA black sites]
-
A.
detainedPrisonersFrom
Indicates that an authority is holding prisoners who originate from or are associated with a specified place or source.
-
B.
carriedPrisonersFrom
chosen
Indicates that an entity transported prisoners away from a specified origin location or source.
-
C.
wasTransportedTo
Indicates that an entity was moved or carried from one location to another, resulting in its arrival at the specified destination.
-
D.
detainedBy
Indicates that an entity is being held in custody or confinement by another entity, typically an authority or controlling party.
-
E.
receivesPrisonersFrom
Indicates that one entity accepts or takes custody of prisoners who are transferred from 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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fe7bfc94bc81909eeec946e8c1c450 |
completed | May 9, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_69fe7b74a1188190886f128e07f712da |
completed | May 9, 2026, 12:10 a.m. |
Created at: May 1, 2026, 12:08 a.m.