DataProvider LtdDiscover a comprehensive dataset marketplace offering enriched, structured, and verified data for analysts, researchers, and professionals.
Explore DatasetsWe offer high-quality, structured datasets verified from reliable platforms such as Wikidata, OpenStreetMap, and historical archives.
Our datasets are ideal for:
Check out BizFinder — our fast, WhatsApp-powered local business discovery tool. You can search nearby businesses, add your own, or claim an existing listing directly via chat or web.
🚀 Visit BizFinderChoose a plan that suits your needs. We offer flexible pricing for individuals, businesses, and enterprises.
| Plan | Features | Price |
|---|---|---|
| Free Tier |
|
£0 / month |
| Pro Tier |
|
£49 / month |
| Enterprise Tier |
|
Contact us for pricing |
Custom Plans: Need something specific? We offer tailored solutions based on your requirements. Get in touch to discuss your needs.
Our APIs allow you to extract verified entities and validate dates from text, images, and PDFs. Below are the available endpoints:
Download Postman Collection: Postman API Collection
Endpoint: POST /api/extract_entities
Description: Extracts and verifies entities (People, Organizations, and Locations) from text, images, and PDFs using Wikidata.
Supported Formats: JSON (text input), Image (JPG/PNG), and PDF.
Request Format (Text):
{ "text": "Sample text containing entities." }Request Format (File Upload - Image/PDF):
Content-Type: multipart/form-data
File: (Upload Image or PDF file)Response Format:
{
"Verified People": "John Doe, Jane Smith",
"Verified Organizations": "Google, Microsoft",
"Verified Locations": "London, New York"
}Error Response:
{
"error": "Invalid input. 'name' key is required."
}Endpoint: POST /api/extract_dates
Description: Extracts and validates dates from text, images, and PDFs, ensuring historical accuracy.
Request Format (Text):
{ "text": "The event took place on July 4, 1776." }Request Format (File Upload - Image/PDF):
Content-Type: multipart/form-data
File: (Upload Image or PDF file)Response Format:
{
"valid_dates": [
{ "date": "1776", "reason": "Recognized as a historical date" }
]
}Error Response:
{
"error": "Invalid input. 'text' key is required."
}Endpoint: POST /api/organisation_info
Description: Enriches the organization record by linking additional metadata. This may include details for companies, institutions, or other entities related to the organization along with extra contextual information.
Request Format:
{
"query": "Organisation Name"
}Response Format:
{
"organization": {
"name": "Organization Name",
"metadata": {
"linked_companies": ["Company A", "Company B"],
"institutions": ["Institution X", "Institution Y"],
"additional_info": "Other relevant metadata details"
}
}
}Error Response:
{
"error": "Invalid input. 'query' key is required."
}Endpoint: POST /api/person_info
Description: Retrieves enriched information for a person. The response includes details such as summaries, dates, or other relevant metadata associated with the individual.
Request Format:
{
"query": "Person Name here"
}Response Format:
{
"person_info": {
"name": "Person Name here",
"details": "Enriched information such as summaries, dates, and additional metadata"
}
}Error Response:
{
"error": "Invalid input. 'query' key is required."
}Endpoint: POST /api/extract-context
Description: Extracts contextual information, dates, and entities from a given webpage URL.
Request Format:
{
"url": "https://example.com/sample-page"
}Response Format:
{
"url": "https://example.com",
"Addresses": [
{
"city": "wood",
"house": "example house",
"house_number": "176-178",
"postcode": "XXX XX",
"road": "example rd",
"state_district": "sample",
"suburb": "example"
}
],
"Title": "Example Title",
"Heading": "Example H1 Heading",
"People": {},
"Organizations": {
"Example Corp": { "context": "Industry-leading company.", "source": "text" }
},
"business_name": [
"Example Business"
],
"Locations": {},
"Dates": {
"2024": { "context": "Event date: 2024", "source": "text" }
},
"Emails": ["info@example.com"],
"Phone Numbers": ["+1 234-567-8901"],
"Metadata": {
"Canonical URL": "https://example.com",
"Meta Description": "This is an example page.",
"Open Graph Tags": { "image": "https://example.com/image.jpg" },
"Images": ["https://example.com/logo.png"],
"External Links": ["https://external-site.com"],
"Internal Links": ["/about", "/contact"],
"Headings": { "H1": ["Example H1 Heading"], "H2": ["Subheading"] }
},
"whois": [
"Business name ",
{
"creation_date": "Thu, 30 Aug 2012 00:00:00 GMT",
"domain_name": "example.co.uk",
"expiration_date": "Sat, 30 Aug 2025 00:00:00 GMT",
"name_servers": [
],
"registrant_city": null,
"registrant_country": null,
"registrant_name": null,
"registrant_street": null,
"registrant_type": null,
"registrar": "Ionos SE [Tag = 1AND1]",
"registrar_url": "https://ionos.com",
"status": "Registered until expiry date.",
"updated_date": "Thu, 29 Aug 2024 00:00:00 GMT"
}
]
}Error Response:
{
"error": "Invalid input. 'url' key is required."
}Currently, our APIs do not require authentication for basic access. However, for high-volume usage or premium datasets, please contact us for an API key.