eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star Knowledge Graphs
Xinyi Pan, Daniel Hernández, Philipp Seifer, Ralf Lämmel, Steffen Staab
TL;DR
The paper tackles the challenge of representing and querying epistemic beliefs in RDF-star knowledge graphs where statements can assert or refute other statements. It introduces eSPARQL, a language that extends SPARQL-star with a four-valued bilattice $\mathcal{FOUR}$ and a FROM BELIEF construct to handle true, false, unknown, and conflicted beliefs across multiple contexts, including nesting of beliefs. The core methodological contribution is a $\mathcal{K}$-annotated SPARQL-star algebra, instantiated with concrete semirings $\mathcal{FOUR}_{th}$ and $\mathcal{FOUR}_{in}$, together with formal semantics for BELIEF and standard SPARQL operators, enabling four key use cases (U1–U4) for epistemic querying. The work discusses the finite-support property, potential non-finite support for certain bilattice operations, practical implementation on Apache Jena, and implications for querying across conflicting or nested belief states in large, multi-source knowledge graphs.
Abstract
Over the past few years, we have seen the emergence of large knowledge graphs combining information from multiple sources. Sometimes, this information is provided in the form of assertions about other assertions, defining contexts where assertions are valid. A recent extension to RDF which admits statements over statements, called RDF-star, is in revision to become a W3C standard. However, there is no proposal for a semantics of these RDF-star statements nor a built-in facility to operate over them. In this paper, we propose a query language for epistemic RDF-star metadata based on a four-valued logic, called eSPARQL. Our proposed query language extends SPARQL-star, the query language for RDF-star, with a new type of FROM clause to facilitate operating with multiple and sometimes conflicting beliefs. We show that the proposed query language can express four use case queries, including the following features: (i) querying the belief of an individual, (ii) the aggregating of beliefs, (iii) querying who is conflicting with somebody, and (iv) beliefs about beliefs (i.e., nesting of beliefs).