The acquisition of commonsense knowledge remains a core challenge in both robotics and artificial intelligence. While Large Language Models (LLMs) encode rich latent knowledge, their unstructured and probabilistic nature limits their direct use in safety-critical domains like robotics. In this paper, we present a pipeline for extracting structured commonsense knowledge from LLMs and integrating it into a symbolic knowledge graph based on the Ontology for Robotic Knowledge Acquisition (ORKA). Grounded in the theory of conceptual spaces, our method targets physical object properties—both categorical (e.g., shape, material, location) and quantifiable (e.g., size, weight, temperature)—relevant to embodied reasoning. We evaluate the pipeline across a diverse set of LLMs, model sizes, and quantization levels, using human-annotated ground truth to assess accuracy. Results show that even compact and quantized models can produce reliable, interpretable knowledge. We also analyze the influence of measurement units and contextual relevance, highlighting trade-offs between model types and use cases. These results indicate that even smaller LLMs can serve as a useful intermediate source for deriving structured commonsense representations in robotics contexts.

National intelligence agencies have the complex task of investigating threats to the national security within strict legal and policy frameworks. Reconstructing the context of investigative decisions for post-analysis and compliance checks is prone to error and labour-intensive. To address this, we propose to capture decision-making processes and their rationale directly using an OWL-based ontology. This approach overcomes the limitations of traditional data management and existing decision ontologies in handling the intricate data dependencies within threat intelligence (TI) decision-making. The result is the Threat Intelligence Decision Ontology (TIDO), which structures analysts’ decision-making while incrementally capturing a decision trace for post-analysis as investigations unfold. The ontology was developed under the complex constraints of safeguarding threat intelligence practices and case information, and validated through competency questions from intelligence experts from the Dutch Defence Intelligence and Security Service (DISS). TIDO offers a novel solution for capturing and understanding decision processes within the sensitive domain of threat intelligence, and evidence-based decision-making in general.

Hybrid Intelligence (HI) is a rapidly growing field aiming at creating collaborative systems where humans and intelligent machines cooperate in mixed teams towards shared goals. A clear characterization of the tasks and knowledge exchanged by the agents in HI applications is still missing, hampering both standardization and reuse when designing new HI systems. Knowledge Engineering (KE) methods have been used to solve such issue through the formalization of tasks and roles in knowledge-intensive processes. We investigate whether KE methods can be applied to HI scenarios, and specifically whether common, reusable elements such as knowledge roles, tasks and subtasks can be identified in contexts where symbolic, subsymbolic and human-in-the-loop components are involved. We first adapt the well-known CommonKADS methodology to HI, and then use it to analyze several HI projects and identify common tasks. The results are (i) a high-level ontology of HI knowledge roles, (ii) a set of novel, HI-specific tasks and (iii) an open repository to store scenarios1 – allowing reuse, validation and design of existing and new HI applications.

Automatically detecting and measuring differences between evolving Knowledge Graphs (KGs) has been a topic of investigation for years. With the rising popularity of embedding methods, we investigate the possibility of using embeddings to detect Concept Shift in evolving KGs. Specifically, we go deeper into the usage of nearest neighbour set comparison as the basis for a similarity measure, and show why this approach is conceptually problematic. As an alternative, we explore the possibility of using clustering methods. This paper serves to (i) inform the community about the challenges that arise when using KG embeddings for the comparison of different versions of a KG specifically, (ii) investigate how this is supported by theories on knowledge representation and semantic representation in NLP and (iii) take the first steps into the direction of valuable representation of semantics within KGs for comparison.

Web vocabularies (WV) have become a fundamental tool for structuring Web data: over 10 million sites use structured data formats and ontologies to markup content. Maintaining these vocabularies and keeping up with their changes are manual tasks with very limited automated support, impacting both publishers and users. Existing work shows that machine learning can be used to reliably predict vocabulary changes, but on specific domains (e.g. biomedicine) and with limited explanations on the impact of changes (e.g. their type, frequency, etc.). In this paper, we describe a framework that uses various supervised learning models to learn and predict changes in versioned vocabularies, independent of their domain. Using well-established results in ontology evolution we extract domain-agnostic and human-interpretable features and explain their influence on change predictability. Applying our method on 139 WV from 9 different domains, we find that ontology structural and instance data, the number of versions, and the release frequency highly correlate with predictability of change. These results can pave the way towards integrating predictive models into knowledge engineering practices and methods.

In a large and decentralised knowledge representation system such as the Web of Data, it is common for data sets to overlap. In the absence of a central naming authority, semantic heterogeneity is inevitable as such overlapping contents are described using different schemas. To overcome this problem, a number of solutions have automated the integration of these data sets by matching their schemas. In this work, we focus on a specific category of these solutions that relies on the concepts' extension for matching the schemas (i.e., instance-based methods). Rather than introducing a new approach for the task of schema matching, this work studies the impact of exploiting the semantics of owl:sameAs in such instance-based methods. For this empirical analysis, we investigate more than 900K concepts extracted from the Web, and make use of over 35B implicit identity assertions to study their impact. The experiments show that despite the growing doubts over their quality, exploiting owl:sameAs assertions extracted from the Web can improve instance-based schema matching techniques.