AI Research

From Queries to Narratives: Cultural Heritage Data... | AI Research

Key Takeaways

From Queries to Narratives: Cultural Heritage Data Stories for Knowledge Graph Exploration and Quality Assessment This paper addresses the challenge of makin...
Cultural-heritage KGs such as the NFDI4Culture-KG contain millions of triples about artworks, music, inscriptions, historical events, and the people and places connected to them.
For many users, however, discovering this knowledge can be difficult.
While SPARQL can be learned, writing meaningful queries first requires an in-depth understanding of the graph's data model, an investment many domain researchers and practitioners are unwilling to make.
In this contribution, a data story is understood as a narrative document that integrates explanatory text and images with executable SPARQL queries and their visualized results.

Paper AbstractExpand

Cultural-heritage KGs such as the NFDI4Culture-KG contain millions of triples about artworks, music, inscriptions, historical events, and the people and places connected to them. For many users, however, discovering this knowledge can be difficult. While SPARQL can be learned, writing meaningful queries first requires an in-depth understanding of the graph's data model, an investment many domain researchers and practitioners are unwilling to make. Even with existing user interfaces, a starting point and some guidance are usually needed, because the data contained in the graph is highly specialized, heterogeneous, and constantly growing, making it challenging to know what it contains or which questions it can answer. In this paper, we present data stories as a way not only to lower this barrier, but also to turn exploration into data-quality assessment, and thus combine accessible querying with the discovery of issues that remain hidden in aggregate statistics. In this contribution, a data story is understood as a narrative document that integrates explanatory text and images with executable SPARQL queries and their visualized results. It is described how they are authored against the graph and how they serve several purposes: guiding users through an unfamiliar graph, creating reproducible narratives, and surfacing data-quality issues previously hidden in aggregate statistics. The authoring platform LODEON including its Sparnatural and AI-supported authoring assistants is introduced as a proof-of-concept. Within the authoring environment, every claim made about the data can be backed by an explicit query, making these narratives transparent and reproducible. This paper also reflects on lessons learned from hands-on seminars and workshops. Early experience suggests that such data stories make cultural-heritage knowledge graphs more accessible for both exploration and quality assessment.

From Queries to Narratives: Cultural Heritage Data Stories for Knowledge Graph Exploration and Quality Assessment
This paper addresses the challenge of making large, complex cultural-heritage knowledge graphs accessible to researchers and the public. While these graphs contain millions of records about art, music, and history, they are often difficult to navigate because they require specialized knowledge of complex data models and query languages like SPARQL. The authors propose "data stories"—narrative documents that combine explanatory text and images with live, executable queries—to guide users through the data, ensure research reproducibility, and help identify hidden data-quality issues. The ai search story also surfaces in Stanford AI discovery identifies natural weight..., adding another angle.

Bridging the Gap with Data Stories

The authors argue that traditional methods of exploring knowledge graphs, such as public SPARQL endpoints or static documentation, are often insufficient for domain experts who lack technical training. Data stories serve as a bridge by providing a guided, narrative-driven experience. By embedding live queries directly into a story, the system allows readers to see exactly how a claim is supported by the underlying data. Because these queries run against the live graph, the results remain accurate as the data grows, and readers can inspect or modify the code to answer their own related questions.

The LODEON Authoring Platform

To move from consuming stories to creating them, the authors introduced LODEON, a proof-of-concept workbench designed to simplify the authoring process. LODEON integrates several tools into a single environment: a WYSIWYG note-taking interface, the Sparnatural visual query builder, and an AI-assisted helper. The AI assistant helps users explore the graph, validate queries, and suggest visualizations without needing to write complex code from scratch. The platform also includes a metadata panel, allowing authors to document contributors, licenses, and persistent identifiers, ensuring that the resulting stories can be cited and reused as formal research outputs. The same large language models question is explored in Geospatial AI, Dataverse Metadata, and the..., which adds a research perspective.

Insights from Practice

The development of these tools was informed by hands-on seminars and workshops, where students and researchers used earlier versions of the technology to explore cultural-heritage data. These sessions revealed that while users appreciated the ability to visualize data and create narratives, writing SPARQL queries remained a significant barrier for beginners. This feedback directly motivated the inclusion of the AI-supported assistant and visual query builders in LODEON. Early experiences suggest that this approach effectively turns data exploration into a structured, purposeful activity, helping users understand both the content of the graph and the quality of the data within it. The ai search story also surfaces in New AI Architecture Mimics the Human..., adding another angle. as detailed in the full paper on Arxiv

Comments (0)

No comments yet

Be the first to share your thoughts!