Triple
T23089500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antonivka Road Bridge |
E575704
|
entity |
| Predicate | wasMilitaryTargetIn |
P24107
|
FINISHED |
| Object | Russian invasion of Ukraine |
—
|
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: Russian invasion of Ukraine | Statement: [Antonivka Road Bridge, wasMilitaryTargetIn, Russian invasion of Ukraine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasMilitaryTargetIn Context triple: [Antonivka Road Bridge, wasMilitaryTargetIn, Russian invasion of Ukraine]
-
A.
bombardmentMilitaryTargets
Indicates the action of directing explosive or artillery attacks specifically against military objectives or installations.
-
B.
wasTargetDuring
chosen
Indicates that an entity served as the target of another entity or action during a specified time period or event.
-
C.
militaryObjectiveOf
Indicates that something serves as a military target, goal, or purpose specifically associated with a given actor or force.
-
D.
civilianTarget
Indicates that the action or operation is directed at, affects, or designates civilians or civilian objects as the target.
-
E.
isMilitaryAssetOf
Indicates that something functions as a military resource, equipment, or facility that belongs to, is controlled by, or is used by a particular 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_69e245bf3e3c819086d3448720efc01b |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18da8818481908d768a0462f3f837 |
completed | April 29, 2026, 4:48 a.m. |
| PD | Predicate disambiguation | batch_69ef89e5ce748190b2c3ac3843484127 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:57 p.m.