Bounded Descriptions for Knowledge Graph Traversal by Language Models

Henselmann D, Harth A (2026)


Publication Type: Conference contribution

Publication year: 2026

Journal

Publisher: Springer Science and Business Media Deutschland GmbH

Book Volume: 16549 LNCS

Pages Range: 379-397

Conference Proceedings Title: Lecture Notes in Computer Science

Event location: Dubrovnik, HRV

ISBN: 9783032251558

DOI: 10.1007/978-3-032-25156-5_20

Abstract

A bounded description of a resource is a useful default subgraph that represents relevant information. When accessing RDF knowledge graphs, bounded descriptions are returned for SPARQL DESCRIBE queries or for HTTP GET requests on Linked Data. Concise Bounded Description (CBD) is the de facto default, but only provides conditional reachability of connected resources, limiting its usefulness for knowledge graph traversal. This paper outlines alternative bounded description specifications consisting of chained and parallel combinations of construction steps. Furthermore, characteristics of bounded description specifications are introduced, including ontology awareness, applicability, and reachability. The evaluation challenges the traversal of a knowledge graph with n-ary relations using retrieved bounded descriptions. Results confirm limitations of the CBD specification, highlight the impact of reachability, and bring attention to ontology-aware and set-specific bounded descriptions.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Henselmann, D., & Harth, A. (2026). Bounded Descriptions for Knowledge Graph Traversal by Language Models. In Maribel Acosta, Marieke van Erp, Sebastian Rudolph, Olaf Hartig, Blerina Spahiu, Anisa Rula, Daniel Garijo, Francesco Osborne (Eds.), Lecture Notes in Computer Science (pp. 379-397). Dubrovnik, HRV: Springer Science and Business Media Deutschland GmbH.

MLA:

Henselmann, Daniel, and Andreas Harth. "Bounded Descriptions for Knowledge Graph Traversal by Language Models." Proceedings of the 23rd European Semantic Web Conference, ESWC 2026, Dubrovnik, HRV Ed. Maribel Acosta, Marieke van Erp, Sebastian Rudolph, Olaf Hartig, Blerina Spahiu, Anisa Rula, Daniel Garijo, Francesco Osborne, Springer Science and Business Media Deutschland GmbH, 2026. 379-397.

BibTeX: Download