Triple
T7944513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SolarWinds |
E184465
|
entity |
| Predicate | cyberattackAttributedTo |
P31290
|
FINISHED |
| Object | suspected Russian state-sponsored actors |
—
|
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: suspected Russian state-sponsored actors | Statement: [SolarWinds, cyberattackAttributedTo, suspected Russian state-sponsored actors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cyberattackAttributedTo Context triple: [SolarWinds, cyberattackAttributedTo, suspected Russian state-sponsored actors]
-
A.
attacker
Indicates a relationship where one entity initiates a harmful or hostile action against another entity.
-
B.
attackerSide
Indicates which party or faction is responsible for carrying out an attack in a conflict or violent incident.
-
C.
allegedAgentOf
chosen
Indicates that one entity is claimed or suspected, but not confirmed, to be the agent responsible for an action or event involving another entity.
-
D.
attackedFrom
Indicates that one entity initiated an attack against another entity originating from a specific source location or position.
-
E.
coordinatedAttacksAlsoTargeted
Indicates that in a set of coordinated attacks, the same target was also attacked as part of those coordinated actions.
- 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_69ca8291c2008190b1b8832c87814bcf |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3b0e84448190a7e8e0749776a592 |
completed | March 31, 2026, 3:10 a.m. |
| PD | Predicate disambiguation | batch_69cae93526d081909303265bf60419fd |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:09 p.m.