Extract shareholder and ownership details from company documents
Structured shareholder data from registers or registry extracts, with totals checks, ownership-threshold flags, and follow-up questions.
The prompt
Extract shareholder and ownership information from a company document into structured data.
Document: [PASTE text from a shareholder register, company registry extract, cap table, or annual return]
Purpose: [e.g. "KYC onboarding", "due diligence", "beneficial ownership check"]
Ownership threshold to flag: [e.g. "25%", "10%"]
Output format: [JSON / table]
Rules:
- Extract only what the document states. If a field is missing or unreadable, use null. Never guess names, numbers, or dates.
- Keep names exactly as written, including legal suffixes (Ltd, GmbH, LLC).
- Distinguish individuals from legal entities. For entities, capture the registration number and registry where shown.
- If share amounts and percentages don't reconcile, keep both and flag the conflict.
- If the document is partial, corrupted, or not a shareholder record, say so instead of forcing output.
For each shareholder return: shareholder_name, type (individual or entity), registration_number_and_registry, address, date_of_birth (individuals, only if shown), nationality_or_jurisdiction, share_class, number_of_shares, share_percentage, voting_rights_if_different, date_acquired, source_location (page or section).
Then add:
1. Totals check: do the percentages add up to 100%? List any gap.
2. Flags: shareholders at or above my threshold; entities whose own owners must be traced to identify the ultimate beneficial owners; nominee or trustee arrangements; inconsistencies.
3. Follow-up: questions or documents to request.
If I chose JSON, return valid JSON only inside one code block, followed by the checks and flags.
Use the personal data only for the stated purpose and in line with my organization's data protection rules.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Legal & Compliance prompts
What to fill in
- e.g. "25%", "10%"
- JSON / table
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Check my AI workflow for privacy and data-protection risksMaps the personal and confidential data in an AI-assisted process and flags privacy and compliance risks to fix before launch.
- Track usage rights for talent, music, and stock in a campaignA rights register showing what every asset is licensed for, where and until when, plus renewal alerts and gaps to clear before launch.
- Respond to a student records request under FERPAWorks out whether to release student records, what to redact, what to log, and drafts the response letter.
- Write a student conduct decision letter that follows due processDrafts a clear, fair discipline decision letter with findings, policy basis, sanction, and appeal rights.