Urban models support sustainable, resilient, and equitable planning, but their validity hinges on underlying spatial data. This study examines the epistemological and technical consequences of relying on two dominant yet divergent platforms—OpenStreetMap (OSM) and Google Maps—for extracting proximity-based amenities within the 15-min city framework. Across four European contexts—Versilia, Gothenburg, Nice, and Vienna—we compare (i) data completeness and spatial coverage; (ii) semantic categories; and (iii) the effects of data heterogeneity on accessibility modelling. Findings show that OSM, while semantically consistent and openly accessible, systematically underrepresents peripheral amenities, introducing bias towards urban cores in accessibility metrics. Conversely, Google Maps provides broader coverage but is constrained by dependencies on extraction methods, opaque data structures, and ambiguous classification schemes, which hinder reproducibility, reduce interpretability, and limit its analytical robustness. These divergences yield distinct accessibility landscapes and competing readings of functionality and spatial equity. We argue that data source choice and protocol design are epistemological decisions and advocate transparent, hybrid strategies with cross-platform semantic harmonisation to strengthen robustness, equity, and policy relevance.