Best Practices

Academic libraries face growing resource volumes and a shortage of experienced catalogers. To address this, the National University of Singapore Libraries initiated the AI-Powered Cataloging (AICAT) Project, exploring how large language models (LLMs) can augment bibliographic metadata creation while maintaining human oversight. This case study shares a practical implementation that generates draft MARC21 records compliant with RDA, ISBD, LCSH, and LCC standards. Utilizing engineered prompts with strict operational constraints—such as hallucination prevention and metadata validation—the project evaluates multiple LLMs to assess accuracy and standards adherence. The three-pronged methodology encompasses prompt engineering, comparative model benchmarking, and workflow automation testing. Results show that AI significantly reduces repetitive cataloging effort and improves scalability, while catalogers retain final editorial authority. Ultimately, effective AI deployment depends on aligning machine outputs with human values through standards-based validation and expert oversight.

Digital game archives require more than descriptive cataloging; they call for a metadata ecosystem that supports both conceptual rigor and practical reusability, underpinning computational use. This paper reports on metadata practices developed at the Ritsumeikan Center for Game Studies (RCGS), organized into three interrelated layers: modeling, linking, and augmenting. These practices are implemented in the RCGS’s online catalog service, the RCGS Collection. At the modeling layer, we develop an extended model based on the IFLA Library Reference Model (LRM) to represent the complex relationships inherent in digital games, including works, variations, packages, and individual items. This approach enables consistent description across heterogeneous archival materials while maintaining compatibility with established bibliographic standards. At the same time, for entities that require subjective interpretation—such as works, genres, franchises, and characters—we design the model to incorporate external authority data. In addition, for the implementation of an online catalog, we employ a “dumb-down” strategy (flattening structured metadata) to improve accessibility for general users. At the linking layer, we implement a Linked Open Data (LOD) approach that connects local entities to external authority sources such as Wikidata and the Media Arts Database (MADB). This alignment supports the persistence of identifiers, enhances interoperability, and enables data enrichment through the incorporation of collectively curated external knowledge. At the augmenting layer, we develop a dataset construction pipeline based on text extraction and image embeddings, transforming digitized materials—including packages, manuals, and gameplay images—into research-ready corpora. Through multimodal feature extraction and automated text structuring, archival data can be repurposed as a resource for computational analysis and metadata generation. These practices are implemented through a SPARQL-enabled LOD infrastructure and a discovery interface based on Omeka S, achieving a balance between a robust identifier infrastructure, machine-readability, and user accessibility. Rather than proposing a prescriptive model, this paper reflects on design decisions and implementation strategies to share insights for building sustainable metadata ecosystems in game archives and related domains.

This presentation shows how the domain-specific “Sampo framework”, here ParliamentSampo for parliamentary speeches and prosopography [1], based on the domain-agnostic Sampo model [2] and Sampo-UI interface model [3-4], can be adapted to new application cases. As an example, our focus here is to show how to publish as a FAIR Linked Open Data (LOD) service the assembly minutes of the League of Nations [5], the predecessor of the United Nations (UN), and to publish next the General Assembly minutes of the UN. As an application on top of the LOD service, the portal League of Nations (1920-1946) Sampo [5] was published on the Web in March 2026. It can be used to answer questions, such as: What have the representatives of Japan talked about? How did the territorial focus of the League of Nations (LoN) shift in time? In what roles and capacity did Fridtjof Nansen, the Polar explorer, participate in LoN meetings? More information about the underlying Minutes of Multilateralism initiative: https://seco.cs.aalto.fi/projects/minutes/ [1] Eero Hyvönen, Laura Sinikallio, Petri Leskinen, Senka Drobac, Rafael Leal, Matti La Mela, Jouni Tuominen, Henna Poikkimäki and Heikki Rantala: Publishing and Using Parliamentary Linked Data on the Semantic Web: ParliamentSampo System for Parliament of Finland. Semantic Web, vol. 16, no. 1, 2025. DOI: 10.3233/SW-243683. https://journals.sagepub.com/doi/full/10.3233/SW-243683 [2] Eero Hyvönen: Digital Humanities on the Semantic Web: Sampo Model and Portal Series. Semantic Web – Interoperability, Usability, Applicability, vol. 14, no. 4, pp. 729-744, IOS Press, 2023. https://journals.sagepub.com/doi/full/10.3233/SW-223034 [3] Heikki Rantala, Annastiina Ahola, Esko Ikkala and Eero Hyvönen: How to create easily a data analytic semantic portal on top of a SPARQL endpoint: introducing the configurable Sampo-UI framework. VOILA! 2023 Visualization and Interaction for Ontologies, Linked Data and Knowledge Graphs 2023, pp. 28-39, CEUR Workshop Proceedings, Vol. 3508, October, 2023. https://ceur-ws.org/Vol-3508/paper3.pdf [4] Esko Ikkala, Eero Hyvönen, Heikki Rantala and Mikko Koho: Sampo-UI: A Full Stack JavaScript Framework for Developing Semantic Portal User Interfaces. Semantic Web – Interoperability, Usability, Applicability, vol. 13, no. 1, pp. 69-84, January, 2022. https://journals.sagepub.com/doi/full/10.3233/SW-210428 [5] Petri Leskinen, Eero Hyvönen, Alexandre Lionnet, Blandine Blukacz-Louisfert, Pierre-Etienne Bourneuf, Davide Rodogno, Grégoire Mallard, and Florian Cafiero: A Linked Open Data Service and Semantic Portal to Study the Assembly Minutes and Prosopography of the League of Nations (1920–1946). The Semantic Web: ESWC 2026, Dubrovnik, Croatia, May 10 - 14, 2026, Proceedings, Springer-Verlag, 2026. In press. https://seco.cs.aalto.fi/publications/2026/leskinen-et-al-lon-2026.pdf