Log inGet started
All tools

Extract Entities

AI
People / organisations / places / dates — four tables with page cites.
New here? This AI tool is free to try.
Create an account and get 5 credits — no card, no daily limit.
Create free accountSign in

What you'll get: four tables — People / Organisations / Places / Dates — with page citations and one-line role notes. For another use, try Extract Contacts (free regex version).

Loading tool…
Private & secure
AI tools process your PDF in memory, send only the extracted text to the model, and discard everything immediately. No file is persisted on our servers.
No watermarks
Clean output, no branding, no daily limits.
Pay only for what you use
Purchased credits never expire. Cancel anytime.

Why people use Extract Entities

Extract Entities surfaces every named person / organization / place / date from a PDF as four structured tables with page citations. Useful for due diligence, legal discovery, news article analysis, research paper coverage maps, and contract review.

Due diligence on a company / individual
Drop a stack of docs (annual reports, news clips, court filings) for a person / company under DD. Get every named connection extracted — faster than manual highlighting and the structured tables surface relationship patterns.
Legal discovery / e-discovery
Litigation docs (emails, contracts, memos) entity-extracted for relationship mapping. Useful for the “who knew what when” analysis where dates + named individuals matter.
News / media coverage map
When a news story develops over weeks (multiple articles compiled into one PDF), entity extraction surfaces who’s appeared in coverage, where, and when. Useful for journalists and analysts tracking complex stories.
Research paper coverage map
What organizations / institutions / authors are cited / acknowledged in a paper. Surfaces collaboration networks and funding relationships beyond the formal author list.
Contract / commitment tracking
Long contracts mention multiple parties, dates, and locations. The structured extraction makes it scannable — useful for the “when does X happen” / “who’s liable for Y” questions during contract administration.

How Extract Entities works

Three steps. Sign in to run, zero retention — files never persisted on our servers.

  1. STEP 1
    Drop the doc
    PDF up to 100 MB. Works on any prose — reports, articles, contracts, emails, transcripts.
  2. STEP 2
    We classify + dedupe
    Server-side extraction, then named-entity-recognition pass classifying mentions into four categories: people, organizations, places, dates. Mentions deduplicated (Mr Sharma / Sharma / Sushil Sharma collapsed when context confirms identity). Page citation on every mention.
  3. STEP 3
    Get four tables
    Markdown tables: PEOPLE / ORGANIZATIONS / PLACES / DATES. Each row: canonical name / mention count / first-page / last-page / sample-context. CSV export for further analysis (Excel, Power BI, etc.).

What makes pdfcraft ai different

  • Citations on every claim
    Every AI summary, answer, and translation links back to the page it came from. You can verify the source before relying on the output. Hallucination is bounded, not blind.
  • Pay only for what you use
    No subscription. Purchased credits never expire. Cancel anytime. Cost shown before you run — exact credit amount appears after upload.
  • Multi-provider routing, no vendor lock-in
    We balance multiple AI providers per call to optimise cost and quality. If one has an outage, the next call automatically tries another. You're not bound to a single vendor's pricing or downtime.
  • Zero retention by design
    Your PDF lives in memory only as long as the AI call needs it, then it's discarded — nothing is persisted to our servers. We don't fine-tune models on your data. Verifiable in your dashboard's audit log.
  • Honest about model limits
    When a doc exceeds the model's context window we surface that the output was truncated (we render result.wasTruncated in every AI tool's UI). When a number can't be verified from the source we flag it. No silent failures.

Frequently asked questions

How accurate is the dedup?
Strong on unambiguous names (Mr Sharma + first reference to Sushil Sharma in same paragraph → same person). Weaker when names overlap (two people named Sharma in different contexts). Manual review of the dedupe column catches false merges.
Will it work for Indian names?
Yes — Indian naming conventions (single names, multi-part regional names, surname-first vs surname-last patterns) recognized. Typical Indian organizations (Reliance, TCS, Infosys, Tata, Adani, HDFC, ICICI etc.) pre-recognized to improve dedup.
Does it identify relationships between entities?
Surfaces co-occurrence (X and Y mentioned in same context) but doesn’t formally classify the relationship (employer / partner / counterparty). For relationship classification, supplement with manual analysis or a graph-database tool.
What about places — will it handle Indian regions?
Indian states, cities, and regions recognized. Smaller localities (towns, neighborhoods) may be classified imperfectly — the model’s knowledge of Indian micro-geography degrades below the city level.
What’s the credit cost?
3 credits per doc. Cost is fixed regardless of doc size.
Privacy?
Doc sent to inference provider for entity extraction, not stored. For sensitive entity-rich docs (DD reports, legal filings), redact metadata via Redact PDF first if needed; structural extraction works on the redacted version.

Want to know how the entities are talked about?

Sentiment Analysis classifies sentiment per-section with evidence quotes. Pairs naturally with entity extraction for the “who’s being talked about and how” analysis.

Try Sentiment Analysis

Related PDF tools

Other tools in the AI category — built on the same private, in-browser pipeline.

We use a first-party cookie to keep you signed in. Product analytics (Google Analytics 4, Microsoft Clarity) are optional and only load if you accept. You can change this any time on the cookies page.
Customize