Triple
T38532916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | General armii |
E923413
|
entity |
| Predicate | usedBySuccessorState |
P167713
|
FINISHED |
| Object | Russian Federation |
—
|
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: Russian Federation | Statement: [General armii, usedBySuccessorState, Russian Federation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedBySuccessorState Context triple: [General armii, usedBySuccessorState, Russian Federation]
-
A.
successorStateUse
chosen
Indicates that one state or condition directly follows and is used as the next state resulting from a prior state or action.
-
B.
associatedWithSuccessorState
Indicates a relationship where something is linked or connected to the state that immediately follows it in a sequence or progression.
-
C.
appliesToSuccessorState
Indicates that the relationship or condition holds not in the current state but in the immediately following (successor) state of the system or process.
-
D.
successorState
Indicates that one state directly follows another as the immediate next state in a sequence or process.
-
E.
successorStateEnabled
Indicates that a particular state transition is allowed and can be taken as the next state in the process or system.
- 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_69f76ea8f6348190a5c03fb6292bbee3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fdb45537288190b6791078d4a6899f |
completed | May 8, 2026, 10 a.m. |
| PD | Predicate disambiguation | batch_69fdb39ad96481908376d7def9fafc13 |
completed | May 8, 2026, 9:57 a.m. |
Created at: May 3, 2026, 4:32 p.m.