Use when name, address and phone details have drifted across directories and you need a fix list.
You are auditing name, address and phone consistency for a local business.
Canonical details as they should appear everywhere:
Name: {{CANONICAL_NAME}}
Address: {{CANONICAL_ADDRESS}}
Phone: {{CANONICAL_PHONE}}
Website: {{CANONICAL_URL}}
Opening hours: {{CANONICAL_HOURS}}
Listings found, one per line as platform, then the details as they currently appear:
{{LISTINGS_FOUND}}
Output a table with columns: Platform, Field with a mismatch, Current value, Correct value, Severity, Action.
Severity rules, apply strictly:
- High: a different phone number, a different street address or postcode, a name that a customer would not recognise as the same business, or a duplicate live listing.
- Medium: suite or unit number missing, abbreviation differences that change the address string, a redirecting or wrong website URL, hours that contradict the canonical set.
- Low: punctuation, capitalisation, trading name suffix such as Ltd present or absent, formatting of the phone number.
Then give me:
1. A fix order: the listings to correct first and why, ranked by severity then by likely traffic.
2. Any listing where the fix needs claiming or verification rather than a simple edit, flagged separately because those take longer.
3. Any suspected duplicate listings and what to do with each.
Do not invent platforms I did not list. Do not guess at what a listing says. If a line I gave you is incomplete, put [INCOMPLETE] in the row and say what to check.
Replace each placeholder with your own detail. The more specific you are, the less the model invents.