Triple
T75479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sinti |
E1508
|
entity |
| Predicate | persecutionType |
P2109
|
FINISHED |
| Object | racial persecution |
—
|
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: racial persecution | Statement: [Sinti, persecutionType, racial persecution]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: persecutionType Context triple: [Sinti, persecutionType, racial persecution]
-
A.
perpetratedBy
Indicates that an action, event, or wrongdoing was carried out or caused by a particular agent or entity.
-
B.
discriminatedAgainst
chosen
Indicates that one entity treats another unfairly or unequally based on a particular characteristic, such as race, gender, or other protected attributes.
-
C.
condemnedBy
Indicates that an entity is judged, denounced, or declared wrong or unacceptable by another entity.
-
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.
punishedBy
Indicates that an entity receives punishment administered by another entity.
- 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_69a24c60d19c8190a1b6c105ca59ef5b |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a25314bd6c81908d1cfd4b83f20049 |
completed | Feb. 28, 2026, 2:29 a.m. |
| PD | Predicate disambiguation | batch_69a24eae77ec81909015906f31f2b62e |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.