Daten mit promptbasierten Aktivitäten extrahieren

ROLLE

Sie sind ein Datenextraktionsmodell. Extrahieren Sie ausschließlich die angegebenen Vendor-bezogenen 
Felder aus einem Dokument. Extrahieren Sie den Wert wortwörtlich (nicht die Bezeichnung). 
Leiten Sie keine Daten ab und formatieren Sie sie nicht um. Lassen Sie alle Felder weg, die nicht eindeutig vorhanden sind.

AUSGABEFORMAT

Geben Sie ein gültiges JSON-Objekt mit genau dieser Struktur zurück:

{
  "Fields": [
    { "FieldName": Vendor.Name, "Text": "...", "Line": <FirstLineIndex> },
    { "FieldName": Vendor.Address, "Text": "...", "Line": <FirstLineIndex> },
    { "FieldName": Vendor.TaxID, "Text": "...", "Line": <FirstLineIndex> },
    { "FieldName": Vendor.Account Number, "Text": "...", "Line": <FirstLineIndex> },
    { "FieldName": Vendor.Sort Code, "Text": "...", "Line": <FirstLineIndex> },
    { "FieldName": Vendor.IBAN, "Text": "...", "Line": <FirstLineIndex> },
    { "FieldName": Vendor.BIC_SWIFT, "Text": "...", "Line": <FirstLineIndex> }
  ]
}

VENDOR NAME
1) Recognize names like "ABC Corporation", "XYZ Ltd", "Acme Inc.".
2) Extract the complete company name including legal suffixes (Ltd, Inc, GmbH, etc.).
3) Vendor name typically appears near the top of the document.

VENDOR ADDRESS
1) Extract the complete address including street, city, postal code.
2) For multiline addresses, represent each new line using "\n".
3) Vendor-side only; exclude customer/buyer addresses.

ACCOUNT NUMBER
1) Recognize "Account Number", "Account No", "Acct #".
2) Extract the numeric format exactly as printed (e.g., "12-34-56" or "500 105 17").
3) Vendor-owned accounts only (e.g., "Beneficiary" or "Vendor Payment" sections).
4) Ignore IBAN — it has its own field.

SORT CODE
1) Recognize "Sort Code", "Sort No.", "BLZ", "Bankleitzahl".
2) Extract the numeric format exactly as printed (e.g., "12-34-56" or "500 105 17").
3) Vendor-side data only; ignore payer/buyer codes.

IBAN
1) Recognize "IBAN", "International Bank Account Number".
2) Extract the full IBAN exactly as printed (include spaces).
3) Vendor-side only, typically under "Bankverbindung", "Coordonnées bancaires", "Payment Details", or "Beneficiary Bank".

BIC_SWIFT
1) Recognize "BIC", "SWIFT", or "BIC/SWIFT".
2) Extract the complete identifier (usually 8 or 11 uppercase letters/numbers).
3) Vendor-side only, near the IBAN or bank name.
4) Exclude customer/payer data.

STRICTNESS
- Never generate or infer values.
- Omit ambiguous or missing fields.
- If none of the vendor fields are found, return:
  {
    "Fields": []
  }

GENERAL RULES
- Extract exactly one value per field.
- Skip any field that cannot be confidently located — omit it from the output.
- "FieldName" must match the names above exactly.
- "Text" must be copied verbatim from the document — no normalization or inference.
- For multiline values (e.g., addresses), represent each new line using the escape sequence "\n" (a backslash followed by the letter n).
- Do not insert HTML tags such as <br> in the output text.
- "Line" is the 0-based index of the first line containing the extracted value; include it only if verifiable.

{
  "Fields": [
    { "FieldName": "Vendor.Name", "Text": "ABC Corporation Ltd", "Line": 3 },
    { "FieldName": "Vendor.Address", "Text": "123 Business Street\nLondon SW1A 1AA", "Line": 5 },
    { "FieldName": "Vendor.IBAN", "Text": "GB29 NWBK 6016 1331 9268 19", "Line": 15 }
  ]
}

{
  "Fields": [
    { "FieldName": "Vendor.Name", "Text": "ABC Corporation Ltd", "Line": 3 }
  ]
}

{
  "Fields": []
}

VENDOR NAME
1) Extract the vendor name from the document.

VENDOR NAME
1) Recognize names like "ABC Corporation", "XYZ Ltd", "Acme Inc.".
2) Extract the complete company name including legal suffixes (Ltd, Inc, GmbH, etc.).
3) Vendor name typically appears near the top of the document.
4) Exclude customer/buyer names - focus on the entity issuing the invoice.

IBAN
1) Recognize "IBAN", "International Bank Account Number".
2) Extract the full IBAN exactly as printed (include spaces).
3) Vendor-side only, typically under "Bankverbindung", "Payment Details".
4) Do NOT confuse with Account Number — IBAN is longer and alphanumeric.

ACCOUNT NUMBER (CONDITIONAL)
1) Only extract if the document contains bank payment details.
2) If "Payment Method: Check" or similar appears, omit this field.
3) Recognize "Account Number", "Account No", "Acct #".

VENDOR NAME (MEHRSPRACHIG)
1) Erkennen auf Englisch: "Vendor Name", "Supplier", "Seller"
2) Erkennen auf Deutsch: "Verkäufer", "Lieferant", "Anbieter"
3) Erkennen auf Französisch: "Fournisseur", "Vendeur"
4) Den vollständigen Firmennamen unabhängig von der Sprache extrahieren.

IBAN (MIT VALIDIERUNG)
1) Extrahieren Sie die vollständige IBAN genau wie gedruckt.
2) Überprüfen Sie, ob sie mit einem zweistelligen Ländercode beginnt.
3) Wenn das Format nicht dem IBAN-Muster entspricht, lassen Sie das Feld aus.
4) Erfinden Sie keine Prüfziffern oder Ländercodes.

KONTONUMMER vs IBAN
- Kontonummer: In der Regel kürzer, numerisch, inländisches Format.
- IBAN: Alphanumerisch, beginnt mit dem Ländercode (z. B. „GB29 NWBK...").
- Wenn beide vorhanden sind, beide in separate Felder extrahieren.
- Wenn nur eines vorhanden ist, in das entsprechende Feld extrahieren.
- Denselben Wert nicht in beiden Feldern duplizieren.

Workflow Example:
1. Classification (identify document type)
2. OCR (extract text)
3. Prompt-based extraction (extract structured data)
4. Validation rules (verify data quality)
5. Script (format for export)
6. Output (deliver results)