Ieva Pigozne | Daniel Antal

Mari Clothing Heritage Across Collections

Thu, 22 Jan 2026 08:45:00 +0100

Read our Substack blogpost

Rather than building a new platform or launching a large institutional programme, we focused on a carefully designed, hands-on intervention. The goal was to create a concrete, working example that could be expanded, criticised, reused, and—crucially—taken up by others. Continue reading on Substack…

WikiMuseum = GLAM Wiki + Wikibase + Data Sharing Space

Sun, 28 Sep 2025 14:00:00 +0200

14:30–15:00 Our presentation took place in the session
GLAM Cooperation and Community Exhibitions at Wikimedia CEE Meeting 2025 in Thessaloniki.

We invite Wikimedia communities, data curators, AI specialists, GLAM partners, and digital humanists to join us in building a multilingual, interoperable Wikimuseum and extending the Finno-Ugric Data Sharing Space.
👉 Read more about this data sharing space

Our talk introduced the Wikimuseum concept: collaborative, multilingual exhibitions that bring together museum objects, archival documents, photographs, and private collections into Wikimedia-powered virtual showcases. As a case study, we presented the Livonian garment exhibition, where dispersed artefacts from Finland, Estonia, and Latvia were digitally reunited for the first time in a century.

We also showed how this approach interlinks with the Finno-Ugric Data Sharing Space (FUDSS), a demonstration of a rather complex system built around open knowledge graphs and a showcase of a particularly challenging data governance and curation use case involving FAIR and SAFE standards, different jurisdictions, rarely used languages.

Our federated Wikibase-driven dataspace designed for small, endangered, or diasporic heritage communities. The DSS applies the European Interoperability Framework to cultural data, connecting CIDOC-CRM museum records, DCTERMS library metadata, and Wikibase lexemes, while respecting local epistemologies and multilingual vocabularies.

Highlights

How joint Wikimedia exhibitions allow GLAM institutions and citizen scientists to co-curate without moving artefacts physically.
How multilingual Wikibase lexemes and semantic interoperability support endangered languages like Livonian, Võro, and Mari.
How a Wikibase Suite and Lexeme can provide for an alternative incubator for small communities with modern AI support.

The Wikimuseum Livonian clothing exhibition demo: Traditional Livonian Clothing

Next steps

Extend the Livonian and Seto exhibitions with more garments, and photographs.
Extend our music collections and publish ethnomusicologically relevant datasets.
Align the Wikimuseum model with the ECCCH Heritage Digital Twin Ontology.

Livestream recording

You can watch our presentation here, with two of us slightly pale with the virus that went around in the conference rooms:

Linking Garments to Knowledge: TextileBase as an Interdisciplinary Graph for Dress and Textile Research

Mon, 01 Sep 2025 00:00:00 +0000

The article demonstrates how dress history and textile-related research can be enhanced through the interoperability of knowledge provided by a knowledge graph. The growing availability of digital cultural and historical data is not matched by a similar increase in their usability. Therefore, expanding the search radius to collections across disciplines and countries requires harmonisation and interoperability of knowledge. Reprex has created TextileBase – a knowledge base fully interoperable with libraries, archives, museums, the open knowledge system Wikidata, and open science repository systems. The article highlights key considerations when formulating searches and addressing terminology dissimilarities to ensure that data providers working across country, language, or disciplinary boundaries understand the intended meaning. To improve and streamline searchability in libraries for textual sources mentioning relevant historical garments, archives for their contemporary depictions, and museum collections for new artefacts, TextileBase transforms data and metadata into knowledge statements, links terms to an international controlled vocabulary, and carefully compares the works of various research and collection institutions.

TextileBase: Introduction

Thu, 10 Jul 2025 15:00:00 +0200

The July 10 is a hybrid event that you can attend either in person or online. Please register via the contact form or via email. For those who cannot visit this event, we offer an alternative online webinar. (Please fill out your availability here). The start time is 15.00 Central European Summer Time, 14.00 GMT and 16.00 EET. If you physically attend, please arrive a few minutes early.

We warmly invite colleagues, friends, and stakeholders interested in cultural heritage data, digital humanities, and AI-supported research to a light and lively summer seminar on three interconnected initiatives.

Our main focus is on TextileBase – our linked open data platform for dress history
We show a glimpse of our futuristic multi-modal, multi-language graph with data, images, music, audiovisual Finno-Ugric Data Sharing Space, as a way to connect clothing history into a broader regional knowledge platform.
And the Wikimuseum concept for wider impact, co-curated collections and exhibitions.

This informal gathering is not about theoretical publications (although we’re happy to send you preprints!). It’s about showcasing how things actually work, especially when archival depth is shallow and data quality is mixed. There’s a big difference between writing about data integration in a computer lab — and actually building tools that work for researchers and cultural institutions across languages, countries, and platforms.

Topics For Discussion

Each speaker will present a short, live demo or walkthrough (10–12 minutes), followed by Q&A and a casual hybrid meet-up.

Daniel Antal: What is TextileBase? Connecting knowledge across museums, archives, libraries, repositories, Europeana, ECCCH, Wikidata.

Anna Márta Mester: Technical, but not Deep Dive: Using the Wikibase Suite, SPARQL endpoints, and Sampo-UI for comfortable scholarly research.

Ieva Pigozne: Use Case: From years to weeks — how Latgalian data curation paved the way for rapid digitisation of Seto and Livonian datasets. Sneak peek: Finno-Ugric clothing.

Kata Gábor: AI for Cultural Heritage: From multilingual NLP to image annotation and ontology enrichment in noisy or sparse data environments.

Asmah Federico: WikiMuseum: A vision for co-curated, multilingual virtual exhibitions with dispersed physical collections.

Wikibase Interfaces

Entry examples from Linked Open Datasets on Garments from the Latgale Region, from right to left: Q142, Q180, Q179, Q181.

In machine-readable format: https://reprexbase.eu/textilebase/Special:EntityData/Q180.ttl

SPARQL Endpoint

We will place here a few sampe querries:

Latgalian Garments Dataset

Sampo UI

We are going to unveil a similar interactive website on the webinar to the OperaSampo; TextileBase will run on Sampo, following dozens of successful digital humanities projects.

Linked Open Datasets on Garments from the Latgale Region

Mon, 07 Apr 2025 17:00:00 +0100

Entry examples from Linked Open Datasets on Garments from the Latgale Region, from right to left: Q142, Q180, Q179, Q181.

The first published dataset, Linked Open Datasets on Garments from the Latgale Region contains data on Latvian traditional shirts and skirts from the Latgale region in Eastern Latvia. The The female and male shirts, and the skirts in the dataset are handmade and were worn in the 19th century. They represent both festive and daily wear of the local female and male peasants. The shirts are stored at the National History Museum of Latvia and the Ethnographic Open-Air Museum of Latvia. The data contain information on the locality of their origin, their approximate date of creation with various precisions, the materials they are made of, and the way of their fabrication, as well as their purpose of wearing (festive or daily wear) and wearer’s ethnicity and gender. They also include the name of the museum each shirt is stored at, supplemented with its unique inventory number. Data on some sample shirts also include a photo of the shirt.

Check out the properties (relations) in the data model: ListProperties
See every entry in the database: All items

Finno-Ugric Data Sharing Space

Thu, 06 Mar 2025 10:30:00 +0200

We started experimenting with the legal, organisational, semantic and technical challenges of creating a genuinely trustworthy, AI-supported data-sharing space that can find and connect tangible and intangible elements of the Finno-Ugric cultural universes. We were also seeking a better governance model for oversight for the custodians of these endangered, shrinking universes in their language and with little technical knowledge, partly as alternatives to the established Wikipedia to the open knowledge incubation method for small linguistic minorities.

Meet up with some of our team members, Daniel Antal, Britt-Kathleen Mere, Ieva Pigoze, Bogáta Tímár, and Ieva Vīvere during the conference, and do not forget to check out our presentation at the LP05 Session, Digital Insights in Cultural Research, on Mar 6, 2025 10:30 AM — 11:00 AM, or meet up with Kata Gábor and Dániel Antal in Paris, Anna Mester and Mihály Nagy in Budapest in subsequent workshops.

Read more or take a look at our conference poster below:

Download the poster in pdf

See our presentation made in the DNBH 2025 conference in Tartu:

What are the competencies of the system that we are building?

Please check out the demo version of the Finno-Ugric Dataspace or read the long-form project description.