Everyone’s heritage. Within everyone’s reach.
Historical newspapers explored through everyday questions. A pilot combining complex OCR and knowledge access with references to original documents.
What it makes possible
434 pages from five issues converted into 160 searchable documentary pieces.
How it takes shape.
We start with
Digitised 19th-century newspapers and magazines: La Época and Nuevo teatro crítico.
Header0102030405Serial fictionReading orderColumns → blocks → text
01 / 05 · Recognise
The page has a structure.
We detect columns, headings, headers and serial fiction to recover reading order.
↗From an image to identified regions.
RECOVERED TEXT
Real documents · Explanatory workflow visualisationDESPEDIDA
Claro está que para ciertos autores, tal vez para media docena, no es aún mal negocio publicar libros…
✓ Page 301 · Source reference retained
02 / 05 · Check
Return to the original. Always.
We check text against the image and reconstruct paragraphs and footnotes. Corrections keep their evidence.
↗Recovered text with its reference.
Un viaje de novios
Emilia Pardo Bazán
PublicationLa Época
Date30 / 11 / 1881
StructureTitle · Author · Paragraphs
↗ Link to page and region
160searchable pieces
Real documents · Explanatory workflow visualisation03 / 05 · Structure
Every article in its place.
We bring together each piece’s regions. Content, metadata and document references are organised separately.
↗160 pieces from 434 pages.
Your collectionSources and references
Literature
Un viaje
de novios
de novios
1881La Época
Illustration of documentary relationshipsReal documents · Explanatory workflow visualisation04 / 05 · Connect
Content becomes discoverable.
We identify topics and entities with textual evidence. Search combines words and ideas.
↗More paths to the same source.
A NATURAL-LANGUAGE QUERY
«Concepción Arenal’s ideas about the situation of women»
MCPSOURCE FOUND
Tested query and result. Illustrative presentation.Concepción Arenal y sus ideas acerca de la mujer
Nuevo teatro crítico · II, 1893
05 / 05 · Ask
A question opens the archive.
MCP brings sources to AI assistants. Responses can link back to the article and original page.
↗Knowledge within more people’s reach.
Technology recovers and organises. People interpret.1 / 5
Recover what a
simple extraction misses.
From image to structured content
Text becomes available again.
PDF text extraction did not recover this page’s body text. The pilot reconstructed it from the image, separating the heading, page number and two paragraphs.
Claro está que para ciertos autores, tal vez para media docena, no es aún mal negocio publicar libros…Recovered excerpt from the original. Historical spelling is preserved; corrections remain linked to their evidence.
Type: article
Title: DESPEDIDA
Page: 301
Body: 2 paragraphs
Reference: document + page + regionSummary of the extracted structure; not an interface screenshot.
Each piece finds its place.
Layout detection and reading order separate news, headings and Emilia Pardo Bazán’s serialised novel Un viaje de novios. Enrichment then groups each article’s regions and adds topics backed by textual evidence.
Query tested on the sample
«Concepción Arenal’s ideas about the situation of women»
The article Concepción Arenal y sus ideas acerca de la mujer ranked first in all three evaluated search modes. Nuevo teatro crítico, February 1893, PDF pp. 111–146.434 pages5 issues160 pieces
Pilot completed on a documentary sample. A general public service remains to be developed. Images come from the PDFs and recorded pilot results.
A capability that adapts to you
What about your organisation?
This project demonstrates a capability we can adapt to your organisation. Let’s explore how your knowledge can help users and become new services, licences or editions, with less repetitive work.
Balthasar & SpeyrOriginal worksText and notes coveredPeople 132
Max2 results
Maximus ConfessorReferences in the content
Mentioned · DiscussedMax WaltherReferences in the content
Mentioned
A library that lets you follow an idea.
OCR · MCP
Your catalogue, where questions begin.
Conversational catalogue · MCP
More value for people and your organisationYou have the knowledge.
Let’s explore your project ↗You have the knowledge.
Let’s take it further.
New uses for your content, more time for your team and opportunities to earn revenue.