Triple
T26688781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saydnaya prison |
E672818
|
entity |
| Predicate | typeOfAbusesDocumented |
P36524
|
FINISHED |
| Object | beatings |
—
|
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: beatings | Statement: [Saydnaya prison, typeOfAbusesDocumented, beatings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfAbusesDocumented Context triple: [Saydnaya prison, typeOfAbusesDocumented, beatings]
-
A.
typeOfAbuse
chosen
Indicates the specific kind or category of abusive behavior that one entity inflicts on another.
-
B.
typeOfViolationsCovered
Indicates the kinds or categories of violations that are included within the scope of a rule, policy, agreement, or enforcement action.
-
C.
typeOfViolenceAddressed
Indicates the specific form or category of violence that is being targeted, dealt with, or addressed in a given context.
-
D.
hasTypeOfViolence
Indicates that an entity involves, exhibits, or is characterized by a specific kind or category of violent behavior or action.
-
E.
periodOfAbuse
Indicates the time span during which abusive behavior occurred or was experienced.
- 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_69eecda2066c8190a344218afa5e89c1 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69fd231cab588190ad0953dc8f4af8f2 |
completed | May 7, 2026, 11:41 p.m. |
| PD | Predicate disambiguation | batch_69fd1aa3f1c481909fe6e9cab1383551 |
completed | May 7, 2026, 11:05 p.m. |
Created at: April 27, 2026, 3:24 a.m.