Triple
T990887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 3rd Belorussian Front |
E21385
|
entity |
| Predicate | successorCommand |
P4262
|
FINISHED |
| Object | Soviet occupation forces in northern East Prussia |
—
|
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: Soviet occupation forces in northern East Prussia | Statement: [3rd Belorussian Front, successorCommand, Soviet occupation forces in northern East Prussia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorCommand Context triple: [3rd Belorussian Front, successorCommand, Soviet occupation forces in northern East Prussia]
-
A.
successorInCommand
chosen
Indicates that one entity is designated to assume command authority immediately after another entity, typically when the latter is unavailable or their term ends.
-
B.
successorOperator
Indicates that one operator directly follows another in a defined sequence or ordering.
-
C.
successorProcess
Indicates that one process directly follows another in a defined sequence or workflow.
-
D.
successor
Indicates that one entity directly follows another in an ordered sequence or position.
-
E.
successorModel
Indicates that one model is the direct follow-up or replacement for another earlier model.
- 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_69a493c383dc8190a03257f22d4b4183 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4ac27e081908f132115464667b2 |
completed | March 1, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69a4b2adbde48190b07966d0c3179516 |
completed | March 1, 2026, 9:42 p.m. |
Created at: March 1, 2026, 7:41 p.m.