Reasoning over Heterogeneous Geospatial Schemas

Semantic interoperability remains a critical challenge in Spatial Data Infrastructures (SDIs), particularly when aligning authoritative taxonomies with collaborative folksonomies. Traditional alignment tools often fail to bridge the semantic and structural asymmetry between these schemas. This paper evaluates the capability of Large Language Models (LLMs), specifically distinguishing between traditional architectures and emerging Large Reasoning Models (LRMs), to perform semantic alignment between the Brazilian national topographic data model standard (EDGV) and OpenStreetMap (OSM). Using a formal ontology as a prompting scaffold, we tested seven model versions (including ChatGPT 5, DeepSeek R1, and Gemini 2.5) on their ability to bridge the gap between rigid hierarchical classes and the dynamic, ‘long-tail’ vocabulary of the folksonomy. Results reveal a distinct trade-off: while traditional LLMs exhibited ‘lexical rigidity’ and popularity bias—failing to map low-frequency tags—Reasoning Models demonstrated significantly improved capacity for semantic expansion, correctly identifying complex many-to-one (n:1) relationships across linguistic barriers. However, this reasoning depth often came at the cost of ‘hallucination by over-specification’ and syntactic instability in generating OWL code. We conclude that a neuro-symbolic approach, positioning LRMs as ‘Semantic Catalysts’ within a Human-in-the-Loop (HITL) workflow, provides a viable pathway for interoperability, balancing generative power with the need for logical rigor and spatial validation

Geospatial analysis · Interoperability · Ontology · Semantic heterogeneity · Semantic Web · Vocabulary · 3D Modeling in Geospatial Applications · Geographic Information Systems Studies · Semantic Web and Ontologies

• Survey of Hallucination in Natural Language Generation

  Open Access•Ziwei Ji, Nayeon Lee et al.•ACM Computing Surveys•2023

  Incluir item

• A translation approach to portable ontology specifications

  Open Access•Thomas Gruber, Thomas R Gruber•Knowledge Acquisition•1993

  Incluir item

• Cognitive representations of semantic categories.

  Eleanor Rosch•Journal of Experimental…•1975

  Incluir item

• Artificial intelligence studies in cartography

  Yuhao Kang, Song Gao et al.•Cartography and Geographic…•2024

  Incluir item

• Natural categories

  Open Access•Eleanor Rosch, Eleanor H Rosch•Cognitive Psychology•1973

  Incluir item