Triple
T4870015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Kyiv (2022) |
E109063
|
entity |
| Predicate | objectiveOfRussia |
P30325
|
FINISHED |
| Object | capture of Kyiv |
—
|
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: capture of Kyiv | Statement: [Battle of Kyiv (2022), objectiveOfRussia, capture of Kyiv]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: objectiveOfRussia Context triple: [Battle of Kyiv (2022), objectiveOfRussia, capture of Kyiv]
-
A.
SovietObjective
Indicates that the entity represents a goal, target, or strategic aim pursued by the Soviet Union.
-
B.
RussianObjective
chosen
Indicates that an entity has an objective, goal, or target specifically related to Russia (e.g., Russian interests, territory, institutions, or actors).
-
C.
RussoAustrianObjective
Indicates a shared objective or goal jointly pursued by Russian and Austrian parties or forces.
-
D.
objectiveOfUnitedStates
Indicates that something is an official objective or goal pursued by the United States.
-
E.
objectiveOfFrance
Indicates that something is an objective, goal, or aim pursued by France.
- 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_69bd440d96a48190b0c87069adef2af1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ff981fc819080d4466c6fe06cf3 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c28e56081908ee411ac94c3769e |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:27 p.m.