🤖 AI Drafted (Not reviewed)
Extract and persist SVO KnowledgeClaim rows only from existing entities and transcription artifacts
|
|
| Tool id |
extract_svo_only |
| Category |
llm |
| Uses a language model |
yes |
| Needs a generative model |
no |
| Runs over many items |
no |
| Item handling |
batch |
| Structured output |
no |
| Human-verified |
not yet |
What it reads
| Port |
Type |
Required |
What it is |
Documents (documents) |
json |
no |
Selected document metadata, typically from Files.documents |
Barrier (sync) (barrier) |
any |
no |
Optional dependency-only input used by chained presets. |
What it emits
| Port |
Type |
Required |
What it is |
Summary (summary) |
json |
— |
Created/reused claim counts |
Count (count) |
number |
— |
Number of selected atomic documents processed |
Options
| Option |
Type |
Default |
What it does |
document_context |
string |
— |
Corpus framing the text cannot supply, e.g. ‘The personal diary of N.C. Marshall, an American engineer in Colombia.’ First-person statements are attributed to the author named here. Blank = derived from each document’s author metadata when present. |
The prompt it sends
This tool does not send a prompt — it does its work in code.