Triple
T28509364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VirusTotal |
E721440
|
entity |
| Predicate | supportsFileUploadSize |
P31204
|
FINISHED |
| Object | up to 650 MB via web interface (approximate, may change) |
—
|
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: up to 650 MB via web interface (approximate, may change) | Statement: [VirusTotal, supportsFileUploadSize, up to 650 MB via web interface (approximate, may change)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsFileUploadSize Context triple: [VirusTotal, supportsFileUploadSize, up to 650 MB via web interface (approximate, may change)]
-
A.
maxFileSize
chosen
Indicates the maximum allowable size limit for a file in the given context.
-
B.
registerFileSize
Indicates the action of recording or storing the size of a file in a system or data structure.
-
C.
supportsMultipleFiles
Indicates that the subject is capable of handling, processing, or operating on more than one file at the same time.
-
D.
fileNameLimit
Indicates a constraint or maximum allowed length or format for a file’s name in a given context.
-
E.
allowsUploadFrom
Indicates that one entity grants permission for another entity to upload content or data from a specified source.
- 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_69f01a5c072081908c7b04bcf6478da9 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_6a00c486d394819084fe93d5bb11ea1e |
completed | May 10, 2026, 5:46 p.m. |
| PD | Predicate disambiguation | batch_6a00c39d99d48190a94bfa057213499c |
completed | May 10, 2026, 5:42 p.m. |
Created at: April 28, 2026, 3:11 a.m.