{ "document_metadata": { "page_number": "1049", "document_number": "DOJ-OGR-00025272", "date": null, "document_type": "Mail Attachment", "has_handwriting": false, "has_stamps": false }, "full_text": "Page 1049\nMail Attachment\nEpstein 76318-054 IR328255.pdf\nPage 2525\nDOJ-OGR-00025272", "text_blocks": [ { "type": "printed", "content": "Page 1049", "position": "header" }, { "type": "printed", "content": "Mail Attachment", "position": "top" }, { "type": "printed", "content": "Epstein 76318-054 IR328255.pdf", "position": "top" }, { "type": "printed", "content": "Page 2525", "position": "footer" }, { "type": "printed", "content": "DOJ-OGR-00025272", "position": "footer" } ], "entities": { "people": [ "Epstein" ], "organizations": [ "DOJ" ], "locations": [], "dates": [], "reference_numbers": [ "76318-054", "IR328255", "DOJ-OGR-00025272" ] }, "additional_notes": "The document appears to be a page from a larger document or report, with a header and footer indicating page numbers and a document identifier. The content is mostly metadata about an attached PDF file." }