Triple
T25299031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jews in Estonia |
E634295
|
entity |
| Predicate | HolocaustStatus |
P17700
|
FINISHED |
| Object | almost all local Jews murdered or deported |
—
|
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: almost all local Jews murdered or deported | Statement: [Jews in Estonia, HolocaustStatus, almost all local Jews murdered or deported]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: HolocaustStatus Context triple: [Jews in Estonia, HolocaustStatus, almost all local Jews murdered or deported]
-
A.
currentStatusAtAuschwitz
Indicates the person’s present condition, role, or situation specifically while at Auschwitz.
-
B.
HolocaustImpact
chosen
Indicates the effect or consequences that the Holocaust had on individuals, groups, societies, or subsequent events.
-
C.
viewOnHolocaust
Indicates a relationship where an entity expresses or holds a particular opinion, stance, or perspective regarding the Holocaust.
-
D.
onlySurvivingImmediateMemberAfterHolocaust
Indicates that the subject is the sole remaining member of their immediate family who survived the Holocaust.
-
E.
legalStatusInNaziView
Indicates the legal classification or standing an entity was assigned under Nazi ideology and law.
- 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_69e75a9503d48190b80a005c6af0cb50 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48fd5621481909935d022d9275194 |
completed | May 1, 2026, 11:34 a.m. |
| PD | Predicate disambiguation | batch_69f45d06d0388190b36ecde92013624a |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 21, 2026, 1:22 p.m.