Triple
T32851993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stasi prison |
E840275
|
entity |
| Predicate | methodOfAbuse |
P79501
|
FINISHED |
| Object | sleep deprivation |
—
|
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: sleep deprivation | Statement: [Stasi prison, methodOfAbuse, sleep deprivation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: methodOfAbuse Context triple: [Stasi prison, methodOfAbuse, sleep deprivation]
-
A.
typeOfAbuse
Indicates the specific kind or category of abusive behavior that one entity inflicts on another.
-
B.
methodOfInfiltration
Indicates the specific technique or approach used to secretly gain access to or penetrate a target, system, or organization.
-
C.
abuse
Indicates that one entity mistreats, harms, or exploits another entity, often in a repeated or severe manner.
-
D.
usesIntimidationMethods
Indicates that an entity employs threats, coercion, or fear-based tactics to influence or control another entity.
-
E.
useOfTorture
chosen
Indicates the intentional infliction or use of torture by one entity upon another, typically to punish, coerce, intimidate, or extract information.
- 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_69f349412c78819084459850e11d29f7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6f38159d08190980ad639e08f00f4 |
completed | May 3, 2026, 7:04 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d7bee48190b94e0beb48a1d7fa |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:17 a.m.