Triple
T10321521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kurdish militias |
E242147
|
entity |
| Predicate | sometimesEngageIn |
P93367
|
FINISHED |
| Object | human rights abuses |
—
|
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: human rights abuses | Statement: [Kurdish militias, sometimesEngageIn, human rights abuses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sometimesEngageIn Context triple: [Kurdish militias, sometimesEngageIn, human rights abuses]
-
A.
mayEngageIn
Indicates that one entity is permitted or authorized to participate in or perform a particular activity or interaction with another entity.
-
B.
engagementOf
Indicates a relationship where an engagement, commitment, or formal involvement is associated with or attributed to a specific entity.
-
C.
stillInvolvedIn
Indicates that an entity continues to participate in or be associated with a particular activity, role, or relationship at the present time.
-
D.
engagementTo
Indicates a formal promise or commitment between two entities to enter into a future partnership or binding relationship.
-
E.
seeksEngagementWith
Indicates an entity’s active effort or intention to initiate or maintain interaction, involvement, or responsive connection with another entity.
- F. None of above. chosen
Provenance (4 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_69d381ac38808190a8ca7457c85b625b |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d7ccb7ec8190a538cf279e48116e |
completed | April 7, 2026, 10:09 a.m. |
| PD | Predicate disambiguation | batch_69d4d1f64a648190a79980d647898eb0 |
completed | April 7, 2026, 9:44 a.m. |
| PDg | Predicate description generation | batch_69d4d7cada7881908beba55a1dc9ecb9 |
completed | April 7, 2026, 10:09 a.m. |
Created at: April 6, 2026, 11:50 a.m.