Triple
T1055173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hazaras |
E22784
|
entity |
| Predicate | discrimination |
P2109
|
FINISHED |
| Object | sectarian violence in Pakistan |
—
|
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: sectarian violence in Pakistan | Statement: [Hazaras, discrimination, sectarian violence in Pakistan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discrimination Context triple: [Hazaras, discrimination, sectarian violence in Pakistan]
-
A.
discriminatedAgainst
chosen
Indicates that one entity treats another unfairly or unequally based on a particular characteristic, such as race, gender, or other protected attributes.
-
B.
discriminatoryLaw
Indicates that a law treats individuals or groups differently in a way that is biased, unfair, or based on protected characteristics such as race, gender, or religion.
-
C.
distinction
Indicates that one entity is recognized, treated, or classified as different or separate from another.
-
D.
diversity
Indicates the degree to which a set of entities differs along one or more dimensions such as type, attributes, or characteristics.
-
E.
disadvantage
Indicates that one entity is in a less favorable, weaker, or hindered position relative to another in a given 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_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.