Abstract. We construct a new multilingual lexical resource from Wiktionary by disambiguating semantic relations and trans­lations. For this task, we propose and evaluate an automatic disambiguation method that outperforms previous approaches significantly. We additionally introduce a method for inferring new semantic relations based on the disambiguated trans­lations. Our resource fills the gap between expert-built resources suffering from high cost and small size and Wikipedia-based resources that are restricted to encyclopedic knowledge about nouns. We demonstrate this by applying our new resource to measuring monolingual and cross-lingual verb similarity. For the latter, our resource yields better results than Wikipedia and expert-built multilingual wordnets. We make our final resource and the evaluation datasets publicly available.