Triple
T33334981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2022 Russian offensive on Sumy Oblast |
E853509
|
entity |
| Predicate | countryAttackedFrom |
P150760
|
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: [2022 Russian offensive on Sumy Oblast, countryAttackedFrom, Russian Federation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryAttackedFrom Context triple: [2022 Russian offensive on Sumy Oblast, countryAttackedFrom, Russian Federation]
-
A.
countryAttacked
Indicates that one country has carried out an attack against another country.
-
B.
countryAttacker
Indicates that one country is the aggressor or initiator of an attack against another country.
-
C.
countryOfOriginOfAttackers
chosen
Indicates the country from which the attackers originated or are associated in the context of an attack.
-
D.
attackCountry
Indicates that one country initiates a hostile or military action against another country.
-
E.
attackedFrom
Indicates that one entity initiated an attack against another entity originating from a specific source location or position.
- 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_69f34969614c81909cd99661b0902533 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a00a22e32f481909b6006c5b1cdefd3 |
completed | May 10, 2026, 3:20 p.m. |
| PD | Predicate disambiguation | batch_6a00a1bd9c908190b4aa17a61f48126f |
completed | May 10, 2026, 3:18 p.m. |
Created at: May 1, 2026, 1:34 a.m.