Triple
T31952943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Detention Site Black |
E815829
|
entity |
| Predicate | foundToInvolve |
P1256
|
FINISHED |
| Object | torture |
—
|
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: torture | Statement: [Detention Site Black, foundToInvolve, torture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundToInvolve Context triple: [Detention Site Black, foundToInvolve, torture]
-
A.
mayBeInvolvedIn
Indicates that an entity has a possible, but not certain, participation or role in a particular event, activity, or situation.
-
B.
involves
chosen
Indicates that an entity participates in, is a part of, or is implicated within a particular event, process, or relationship.
-
C.
investigationInvolvement
Indicates that an entity participates in, is associated with, or plays a role in a particular investigation.
-
D.
frontInvolved
Indicates that an entity is directly involved in or associated with the front (e.g., front line, front-facing part, or leading edge) of another entity or situation.
-
E.
constantInvolved
Indicates that a constant participates in or is directly involved in the specified relation, operation, or context.
- 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_69fdec5ffe088190ac5505f26c6cff18 |
completed | May 8, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69fdeae15f1c81908fc63fbc1b028d2e |
completed | May 8, 2026, 1:53 p.m. |
Created at: May 1, 2026, 12:08 a.m.