||We investigate the recognition of phone placement in the vicinity of their user using different pattern classification strategies and phone-integrated sensors. The novel approach in our work is to use RFID tags for annotating phone placement. We use the NFC function of smartphones to continuously read tags during training data acquisition at different phone sites. We show that the RFID-based annotation approach requires minimal effort from users to acquire annotated data, enabling users to personalise phone placement recognition. In an evaluation study with 39 hours of phone placement recordings from six participants and four frequently used phone sites, we compare the annotation accuracy of our RFID-based approach to expert-verified annotations. Our results show that RFID-based annotations perform approx. 2% below the expert-verified variant. Personalised classification models outperform models trained from all participants, suggesting that our RFID-based approach is viable for a personalised phone placement recognition. Sub-sequently, we analyse the amount of training data, sensors, and features required to achieve an average recognition rate of 80%.