Autonomous robots that are to assist humans in their daily lives are required, among other things, to recognize and understand the meaning of task-related objects. However, given an open-ended set of tasks, the set of everyday objects that robots will encounter during their lifetime is not foreseeable. That is, robots have to learn and extend their knowledge about previously unknown objects on-the-job. Our approach automatically acquires parts of this knowledge (e.g., the class of an object and its typical location) in form of ranked hypotheses from the Semantic Web using contextual information extracted from observations and experiences made by robots. Thus, by integrating situated robot perception and Semantic Web mining, robots can continuously extend their object knowledge beyond perceptual models which allows them to reason about task-related objects , e.g., when searching for them, robots can infer the most likely object locations. An evaluation of the integrated system on long-term data from real office observations, demonstrates that generated hypotheses can effectively constrain the meaning of objects. Hence, we believe that the proposed system can be an essential component in a lifelong learning framework which acquires knowledge about objects from real world observations.