Triple
T15264079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The DAO hack |
E364853
|
entity |
| Predicate | exploitedComponent |
P67454
|
FINISHED |
| Object | The DAO split function |
—
|
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: The DAO split function | Statement: [The DAO hack, exploitedComponent, The DAO split function]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exploitedComponent Context triple: [The DAO hack, exploitedComponent, The DAO split function]
-
A.
associatedWithVulnerability
chosen
Indicates a relationship where an entity is linked to, affected by, or relevant to a specific vulnerability or security weakness.
-
B.
vulnerabilityType
Indicates the specific kind or category of vulnerability associated with an entity or situation.
-
C.
openSourceComponents
Indicates that one entity uses, includes, or is composed of open-source software components provided by another entity.
-
D.
exploits
Indicates that one entity unfairly or selfishly uses another entity or resource for its own advantage or benefit.
-
E.
usedComponent
Indicates that one entity has employed or incorporated another entity as a component in its structure, function, or operation.
- 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_69d85a0f08408190b3c3259ae35d79d2 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0084fed0481908e452c89cba2be82 |
completed | April 15, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69deca8d1bd48190a4b94f29b425e335 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:14 a.m.