Comprehensive PII (surface forms)
Other languages
Comprehensive PII (surface forms)
Use this template for repeatable PII inventories in Claira: one comma-separated line of quoted values, each surface form exactly as written in the document.
When you select this template, Claira displays the prompt configuration panel. Map the output to a Text review field in your case (this output is not suitable for Date or single-choice fields). Restrict field visibility and follow your organization's data-handling policy when storing raw PII.
What this prompt is for
This template lists every distinct written form of personally identifiable information (PII) without normalization, in a single machine-friendly line. The format works well as input for Search Term Families in Nuix Discover: each quoted value (or a group you treat as one family) can drive grouped search or QC across the collection.
The prompt does not assume any one country. Government-issued identifiers are described by what they do rather than by name, so a Tax File Number, a Steuer-Identifikationsnummer and a Social Insurance Number are all in scope without being listed individually. If you know which country your documents come from, paste the matching block from the Jurisdiction blocks section of this article to improve recall further.
Step-by-step in Claira
- Open Prompting > Template picker in your case.
- Under Investigations, select Comprehensive PII (surface forms) and map the output to one or more Text review fields.
- Replace the
EXPECTED IN THIS COLLECTIONblock with the jurisdiction for your documents, or delete that section entirely: the prompt works either way. - Run a 10 to 25 document sample first; confirm quoting, commas, and the
NO PII DETECTEDsentinel behave as you expect. - Adjust field permissions and workflow settings outside the prompt body, then extend to bulk review.
The prompt
Extract every unique instance of Personally Identifiable Information (PII) from this document. PII includes, but is not limited to: full names, partial names, initials, nicknames, titles with names (e.g., Mr. Doe, Dr. Smith), email addresses, phone numbers, physical addresses, dates of birth, government-issued identifiers, financial account numbers, medical record numbers, IP addresses, and usernames.
Government-issued identifiers are in scope whatever country issued them and whatever they are called locally: tax and revenue numbers, social insurance and social security numbers, national identity numbers, health and medical insurance numbers, passport numbers, and driver's licence numbers all qualify. Treat any number that functions as an official reference to a person as an identifier, even if you do not recognize the scheme.
Do not include dates or URLs that are not contained in email addresses.
EXPECTED IN THIS COLLECTION
>>> REPLACE THIS BLOCK WITH THE JURISDICTIONS IN THIS COLLECTION, OR DELETE THIS SECTION <<<
The block above is a hint about what to expect, never a limit: identifiers and formats from any other country are still PII and must still be extracted.
Follow these rules exactly:
- Output every unique surface form of each PII instance exactly as it appears in the document. If the same person, address, or other entity is written in multiple formats, include each distinct format as a separate entry (e.g., "John Doe", "J. Doe", "Mr. Doe", "Doe, John").
- Do not include duplicates of the exact same formatted string. Each entry in the output must be unique character-for-character.
- Do not normalize, correct, reformat, expand, or abbreviate any value. Preserve original casing, punctuation, spacing, and spelling, including apparent typos.
- For addresses, include each distinct written format separately. The same address counts more than once when the street type is abbreviated in one place and spelled out in another, or when the city, region, or postal code is present in one form and absent in another.
- For phone numbers, include each distinct written format separately. The same number counts more than once when it is written with and without a country code, with different digit groupings, or with different separators (spaces, hyphens, brackets, dots).
- Wrap each value in straight double quotation marks. Separate entries with a comma. Do not use line breaks, bullets, numbering, curly braces, square brackets, or any other wrapper or delimiter.
- Do not include any introductory text, explanatory text, headings, labels, categories, counts, trailing commentary, or closing remarks. The response must begin with the first quotation mark and end with the final quotation mark.
If no PII is found, output exactly: "NO PII DETECTED"Recommended customizations
- Paste a jurisdiction block over the placeholder (the Jurisdiction blocks section of this article has ready-made ones for Canada, Australia, the United Kingdom and Germany/EU), or delete the
EXPECTED IN THIS COLLECTIONheading, the placeholder and the sentence beneath it as one unit if you would rather not narrow the prompt at all. - Add case-specific scope in workflow instructions (custodians, date bounds, document types) without changing the output rules above.
- Keep downstream tooling expectations explicit (e.g., how you split values into Search Term Families).
- Version your configuration so bulk runs stay reproducible.
Jurisdiction blocks
Paste one of these over the >>> REPLACE THIS BLOCK ... <<< line. Naming the identifiers your documents actually contain improves recall on schemes the model might otherwise not read as personal data. Combine two blocks when a collection spans countries.
Canada
This collection is Canadian. Expect SIN, provincial health card numbers, driver's licence numbers and passport numbers; phone numbers as 514-555-0134, (514) 555-0134 or +1 514 555 0134; postal codes as H3A 1B2.Australia
This collection is Australian. Expect Tax File Numbers (TFN), Medicare numbers, ABNs, driver licence numbers and passport numbers; mobiles as 0491 570 156 or +61 491 570 156, landlines as (02) 5550 1234; postcodes as four digits.United Kingdom
This collection is from the United Kingdom. Expect National Insurance numbers, NHS numbers, UTRs, passport numbers and driving licence numbers; phone numbers as 07700 900123, 020 7946 0958 or +44 20 7946 0958; postcodes as SW1A 1AA.Germany and the EU
This collection is German or EU. Expect Steuer-Identifikationsnummer, Sozialversicherungsnummer, Personalausweisnummer, passport numbers and IBANs; phone numbers as 030 23125 100 or +49 30 23125 100; postcodes as five digits.Worked example
Input excerpt
Please contact John Doe at john@acme.co or J. Doe on (02) 5550 1234; the Toronto office reaches him on +1 416 555 0134. Same person also listed as "Doe, John" on the fax cover.Expected output shape
"John Doe","J. Doe","john@acme.co","(02) 5550 1234","+1 416 555 0134","Doe, John"Both numbers are returned, in the form each was written. The prompt does not prefer one country's conventions, so a document that mixes them yields every distinct surface form.
Troubleshooting
- If the model adds labels or line breaks, restate in workflow instructions that the answer must be a single comma-separated quoted list only.
- If a national identifier is being missed, name it explicitly in the
EXPECTED IN THIS COLLECTIONblock. Schemes that look like ordinary reference numbers benefit most from being named. - If OCR quality is poor, PII in unscanned images may be missed: verify extraction text before relying on results.
- If output is too noisy, run this template on a sample first, then narrow scope with a more targeted prompt from the PII Identification workflow.
Related
Was this page helpful?
Need more help?
Contact our support team at support@claira.to — we are here to help.