Quantitative information about entities constitutes a significant portion of tabular data in open sources and data lakes.Such tables often lack consistent labeling and proper schema, posing significant challenges for querying and integration.This paper studies the problem of numerical column annotation in scenarios where quantitative data may be gathered from different sources and unit consistency is a concern.For instance, weight measurements may vary between entities, expressed in kilograms for some and pounds for others, with no accompanying unit information.We investigate the conditions for effectively annotating mixed-unit numeric data, introduce a benchmark for such an annotation task, and propose an algorithm that reliably detects semantic types (e.g., height) and links them to the corresponding types present in a knowledge graph.Our evaluation on a diverse set of columns with mixed units and varying levels of annotation difficulty shows that our method significantly outperforms strong baselines such as GPT-4o-mini and SAND in terms of accuracy, excelling in both detecting mixed units and annotating them with appropriate semantic labels.

A large portion of quantitative information about entities is expressed as Web tables, and these tables often lack proper schema and annotation, which introduces challenges for the purpose of querying and analysis. In this paper, we introduce SAND, a novel approach for annotating numeric columns of Web tables by linking them to properties in a knowledge graph. Our approach relies only on the semantic information readily available in knowledge graphs and not on contextual information that can be missing or labelled data which may be difficult to obtain. We show that our approach can reliably detect both semantic types (e.g., height) and unit labels (e.g., Centimeter) when the semantic type is present in the knowledge graph. Our evaluation on real-world web tables shows that our method outperforms by a large margin, in terms of accuracy, some of the state-of-the-art approaches on semantic labeling and unit detection.