Triple
T31242810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sony Pictures email leak |
E796606
|
entity |
| Predicate | compromisedAsset |
P21464
|
FINISHED |
| Object | corporate emails |
—
|
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: corporate emails | Statement: [Sony Pictures email leak, compromisedAsset, corporate emails]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compromisedAsset Context triple: [Sony Pictures email leak, compromisedAsset, corporate emails]
-
A.
compromisedOn
Indicates that two or more parties reached a mutual agreement by each conceding or adjusting their original positions.
-
B.
associatedWithCompromise
chosen
Indicates a relationship where an entity is linked to, involved in, or affected by a security compromise or breach.
-
C.
vulnerabilitySource
Indicates that one entity is the origin, cause, or contributing factor of another entity’s vulnerability or weakness.
-
D.
securityVulnerability
Indicates that an entity has a weakness or flaw that could be exploited to compromise its security.
-
E.
isExploitedFor
Indicates that one entity is unfairly or abusively used by another entity as a resource, means, or advantage for the latter’s benefit.
- 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_69f224db69ac81909a370adad6a7ac7c |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:11 p.m.