Triple
T2592116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Sea Germans |
E58144
|
entity |
| Predicate | WWIIExperience |
P40056
|
FINISHED |
| Object | mass deportation to Siberia |
—
|
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: mass deportation to Siberia | Statement: [Black Sea Germans, WWIIExperience, mass deportation to Siberia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: WWIIExperience Context triple: [Black Sea Germans, WWIIExperience, mass deportation to Siberia]
-
A.
WWIIEvent
Indicates that the event is part of, or directly related to, the historical period and activities of World War II.
-
B.
WWIITheater
Indicates the geographic or operational theater in which a World War II-related event, action, or entity was involved.
-
C.
sideInWorldWarII
Indicates that an entity was aligned with or participated on a particular side during World War II.
-
D.
WWIIUse
Indicates that one entity made use of another entity during World War II, typically for military, strategic, or wartime-related purposes.
-
E.
statusDuringWorldWarII
Indicates the role, condition, or classification an entity had specifically during the period of World War II.
- F. None of above. chosen
Provenance (4 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_69ab4ac019c8819094add11c46706e32 |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd425851c819088db89713c07056f |
completed | March 7, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69abd0d344988190a18dd93b13e002e6 |
completed | March 7, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69abd2baee308190bdaa41ef1f6bc9cc |
completed | March 7, 2026, 7:24 a.m. |
Created at: March 6, 2026, 9:49 p.m.