DOJ-OGR-00024910.json 1.1 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445
  1. {
  2. "document_metadata": {
  3. "page_number": "433",
  4. "document_number": "DOJ-OGR-00024910",
  5. "date": null,
  6. "document_type": "Mail Attachment",
  7. "has_handwriting": false,
  8. "has_stamps": false
  9. },
  10. "full_text": "Page 433\nMail Attachment\nEP.staffmemos.pdf\nPage 1180\nDOJ-OGR-00024910",
  11. "text_blocks": [
  12. {
  13. "type": "printed",
  14. "content": "Page 433",
  15. "position": "header"
  16. },
  17. {
  18. "type": "printed",
  19. "content": "Mail Attachment\nEP.staffmemos.pdf",
  20. "position": "middle"
  21. },
  22. {
  23. "type": "printed",
  24. "content": "Page 1180",
  25. "position": "footer"
  26. },
  27. {
  28. "type": "printed",
  29. "content": "DOJ-OGR-00024910",
  30. "position": "footer"
  31. }
  32. ],
  33. "entities": {
  34. "people": [],
  35. "organizations": [
  36. "DOJ"
  37. ],
  38. "locations": [],
  39. "dates": [],
  40. "reference_numbers": [
  41. "DOJ-OGR-00024910"
  42. ]
  43. },
  44. "additional_notes": "The document appears to be a page from a larger document, likely a PDF attachment to an email. The content is mostly blank, with some header and footer information."
  45. }