Triple
T34675937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shoah |
E890493
|
entity |
| Predicate | victimGroupAlsoPersecuted |
P22568
|
FINISHED |
| Object | Roma and Sinti |
—
|
NE NERFINISHED |
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: Roma and Sinti | Statement: [Shoah, victimGroupAlsoPersecuted, Roma and Sinti]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: victimGroupAlsoPersecuted Context triple: [Shoah, victimGroupAlsoPersecuted, Roma and Sinti]
-
A.
ethnicGroupPersecuted
chosen
Indicates that a particular ethnic group is subjected to systematic hostility, discrimination, or violence by another party.
-
B.
victimGroup
Indicates that one group or entity is the target or recipient of harm, abuse, or wrongdoing caused by another.
-
C.
persecutionOf
Indicates the act of subjecting an entity to persistent, often unjust hostility, harassment, or oppression, typically on the basis of identity, beliefs, or group membership.
-
D.
persecutedIn
Indicates that an entity is subjected to oppression, harassment, or unfair treatment within a particular place, context, or time period.
-
E.
wasPersecutedBy
Indicates that an entity was subjected to persistent hostility, oppression, or harmful treatment carried out 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_69f349d9c59481908b36baa0be093aea |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f72ad38a208190b4bdc828297f86ad |
completed | May 3, 2026, 11 a.m. |
| PD | Predicate disambiguation | batch_69f72a0243988190a43b8ea22457cd30 |
completed | May 3, 2026, 10:57 a.m. |
Created at: May 1, 2026, 2:05 a.m.