Triple
T1055192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hazaras |
E22784
|
entity |
| Predicate | conflictVictim |
P699
|
FINISHED |
| Object | attacks on Shia mosques and schools in Afghanistan |
—
|
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: attacks on Shia mosques and schools in Afghanistan | Statement: [Hazaras, conflictVictim, attacks on Shia mosques and schools in Afghanistan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conflictVictim Context triple: [Hazaras, conflictVictim, attacks on Shia mosques and schools in Afghanistan]
-
A.
portraysAsVictim
Indicates that one entity represents or depicts another entity as a victim in a given context or narrative.
-
B.
victimGroup
chosen
Indicates that one group or entity is the target or recipient of harm, abuse, or wrongdoing caused by another.
-
C.
victimOccupation
Indicates the profession or job role held by the person who is the victim in an event or incident.
-
D.
notableVictim
Indicates that the subject is a person or entity who is notably recognized as a victim of the object (such as an event, crime, or harmful action).
-
E.
conflictRole
Indicates that an entity plays a specific role or position within a conflict or dispute between parties.
- 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_69a493da02e081908c13ff5e02a0fe7a |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b8d79268819080f3f3f497e91c58 |
completed | March 1, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69a4b731e25c8190b5ea8466648c2c9a |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.