Linguistic Patterns in European Public Organization Names

This work addresses the challenge of classifying public sector organizations across multiple European languages using only their official names, a critical step for entity disambiguation in knowledge graph population. We employ ontology-based knowledge extraction to evaluate three Natural Language Processing approaches: rule-based keyword extraction, zero-shot Natural Language Inference, and embedding-based semantic similarity —under low-context, low-resource assumptions. Large Language Models are integrated accross all three techniques. Our methodology systematically evaluates multilingual preprocessing, various state-of-the-art models, different supervision regimes, classification structures, and parameter optimization. We conduct a detailed evaluation across three specific domains (healthcare, administration, education) spanning all European Union countries, analyzing performance in relation to lexical structure and class balance. Results demonstrate that lightweight rule-based methods, particularly TF-IDF keyword selection, are effective in multilingual scenarios with some training data available. Natural Language Inference models offer competitive zero-shot performance but show deficiencies with unbalanced class distribution. Embedding-based methods provide the most consistent generalization across languages, with evidence of class coherence in vector space. This work highlights the feasibility of ontology-guided model training from short texts and which can prove valid approaches to entity disambiguation challenges in formal knowledge representation systems, particularly when integrating diverse European organizational entities into structured knowledge bases.