Extract Entities
AI / AgentDetect emails, phones, dates, IPs, credit cards, IBANs, currencies, hashtags, and mentions from text.
Despite the "AI tools" category and the NER-adjacent name, this is pure regex and pattern matching, not a language model. It pulls emails, phone numbers, dates, IPs, credit cards, IBANs, currencies, hashtags, and mentions out of unstructured text (a support ticket, a scraped social post, a log dump) into clean structured lists. Well-formatted entities like standard emails and IPs are caught reliably; loosely formatted phone numbers or dates in unusual locales can be missed or misclassified, and since there's no contextual understanding, it can't distinguish a real credit card number from a random 16-digit string beyond checking structural validity like the Luhn checksum. It's a useful first pass before sharing a document externally, catching IPs or IBANs a manual review might miss, but it can't confirm a detected account or card actually exists, only that it's shaped like one.
How to use Extract Entities
- 1.Paste a block of unstructured text (an email thread, support ticket, or log dump) to pull out every email, phone number, and date it contains as structured lists.
- 2.Use it to scan a document for IPs and IBANs before sharing it externally, catching sensitive data you might otherwise miss in a manual review.
- 3.Run scraped social media text through it to extract hashtags and mentions into a clean list for analysis.
Frequently asked questions
Use via API, SDK, or MCP
cURL# Free: 1,000 req/day · Pro: 10,000 req/day
curl -X POST https://api.utilix.tech/v1/tools/extract-entities \
-H "Authorization: Bearer utx_live_..." \
-H "Content-Type: application/json" \
-d '{"text":"Alice works at Anthropic in San Francisco. She met Bob last Tuesday."}'Get an API key from your dashboard · Full API docs →