The EU Data Act establishes comprehensive rules governing data access and sharing across business-to-consumer (B2C), business-to-business (B2B), and business-to-government (B2G) contexts. This paper presents a comprehensive ontology for the EU Data Act, enabling reasoning over data sharing agreements through machine-readable representations. The DAOnt ontology reuses elements from three established ontologies, LKIF-Core, ODRL, and DPV, to capture the normative structure of the Data Act. The ontology captures the main concepts and relationships in the Regulation, and it also operationalises three articles to facilitate compliance checking: Article 4(1) (B2C user access rights), Article 8(6) (B2B trade secret exceptions) and Article 19(2)(a) (B2G competitive use prohibitions). The ontology supports compliance checking through SPARQL queries that return obligations, permissions, and prohibitions, allowing organisations to verify whether data-sharing agreements meet the requirements of the EU Data Act and to assess conditions such as FRAND obligations. By representing key legal concepts in RDF, our work helps bridge the gap between the legal provisions of the Data Act and their computational interpretation. The complete ontology, along with example instances and queries, is available online.
Figures & tables
Figure 1: A top-level diagram of the ontology, depicting most relevant classes. ( Red tiles signify classes from the DAOnt ontology, blue from ODRL , green from DPV )
\cellcolor [HTML]EFEFEF CQG1. General CQs (9 CQs)
\cellcolor [HTML]EFEFEF CQG2. CQs Related to PoC Articles (3 CQs)
CQ1. Who shares data with whom, and under what agreement? CQ2. What actions has a party performed? CQ3. What obligations does a party have? CQ4. Who manufactured a product? CQ5. Who uses a product? CQ6. What service does a product provide? CQ7. When does a legal rule apply? CQ8. Where does data come from? CQ9. Who holds the data?
CQ10. Which data holders have violated Article 4(1) by failing to provide requested data from connected products? CQ11. Which data holders have violated Article 8(6) by refusing data sharing without providing trade secret justification? CQ12. Which public sector bodies have violated Article 19(2)(a) by developing competing products or services using data obtained through B2G data sharing?
Table 1: Competency questions grouped by general coverage (CQG1) and article-specific requirements for the proof of concept (CQG2).
Aspect
Article 4(1) B2C
Article 8(6) B2B
Article 19(2)(a) B2G
Legal Text
”shall make data available without undue delay”
”not required to make data available where data constitute trade secrets”
”shall not use data to develop competing products”
Deontic Type
Obligation ( odrl:Duty )
Permission ( odrl:Permission )
Prohibition ( odrl:Prohibition )
Condition
User requests data access
B2B request + trade secret
None (unconditional)
Action
provideDataAction
refuseDataAccessAction
UseDataToDevelopCompetingProduct
Exception
None
containsTradeSecretCondition
None
Assignee
Data holder (must act)
Data holder (may refuse)
Public sector body (cannot act)
Table 2: Comparison of three Data Act articles
Figure 2: Diagram depicting the principal classes and properties involved in DA Art. 4(1), based on the ODRL design pattern. ( Red tiles signify classes from the DAOnt ontology, blue from ODRL )
Figure 3: Diagram depicting the principal classes and properties involved in DA Art. 8(6), based on the ODRL design pattern. ( Red tiles signify classes from the DAOnt ontology, blue from ODRL , gray signifies XML Schema Definitions)
Figure 4: Diagram depicting the principal classes and properties involved in DA Art. 19(2)(a), based on the ODRL design pattern. ( Red tiles signify classes from the DAOnt ontology, blue from ODRL )
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Figure 5: Complete Ontology Requirements Specification Document (ORSD) for DAOnt.
Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: heterogeneous data resides outside the agent, while the agent can access it (e.g., column names and file paths) only through generic tools. Existing approaches either let agents directly explore raw data sources or inject manually constructed semantic layers into prompts. However, neither scales well to large heterogeneous data sources nor adapts to different agent behaviors. In this paper, we introduce EvoOntology, a self-evolving ontology layer for data agents. EvoOntology encapsulates the ontology as an MCP server comprising a schema layer, a content layer, and a tool layer, enabling agents to actively query and interact with the ontology at runtime. To this end, we introduce a builder agent for autonomous ontology construction and a self-evolution loop that continuously refines the ontology through attribution-guided typed edits that are accepted only after a backbone-conditional paired evaluation. Experiments on three well-adopted data-agent benchmarks with four LLM backbones demonstrate that EvoOntology consistently outperforms strong baselines and existing semantic-layer approaches, effectively bridging the agent-data gap and enabling more effective interaction with heterogeneous data. Code: https://github.com/ruc-datalab/EvoOntology
In ontology-based data access (OBDA), multiple data sources are integrated via mappings to an ontology. We consider an OBDA setting based on existential rules and the certain answer semantics. We address the recent issue of query abstraction, which consists of abstracting data queries by translating them to the ontology layer. Since a perfect abstraction may not exist, the notions of minimally complete and maximally sound abstractions have been introduced. We study abstractions within an extension of UCQs with a limited form of inequality and a special predicate marking database constants. While this extension does not lead to an increased complexity of the problems of interest, it is able to express minimally complete abstractions, hence perfect abstractions when they exist. We also characterize maximally sound abstractions by making a new connection with the notion of maximum recovery stemming from data exchange.
Michel Leclère, Marie-Laure Mugnier, Guillaume Pérution-Kihli
LIRMM, Inria, University of Montpellier, CNRS, Montpellier, France
Enterprise data analysis requires agents to connect analytical requests with knowledge distributed across databases, business documents, and existing example tasks. Without an explicit representation of this knowledge, an agent may produce incorrect analytical results and cannot reliably incorporate feedback. We present AgentOnto, an ontology-guided LLM agent for enterprise data analytics. AgentOnto organizes heterogeneous enterprise knowledge into an ontology that directly guides analysis and incorporates confirmed feedback. Iterative Ontology Preparation further improves the ontology through self-generated analysis tasks. We evaluate AgentOnto on two public data sources. AgentOnto substantially outperforms representative methods, while module-level evaluations confirm the effectiveness of ontology construction, analysis, and updating. A real-world deployment further demonstrates its practical value in enterprise analytics. These results demonstrate that explicitly constructing, using, and updating enterprise knowledge supports reliable and adaptable data analysis.
Dayan Pan, Bincheng Zuo, Xiaojian Wang +2
School of Computer Science and Engineering, Beihang University, Beijing, China · Omaha AIGC, Shanghai, China