Evaluation results for the two baselines (generic neural NER model and Microsoft Presidio) on the development and test sections of the TAB corpus. We report both the standard, token-level recall R_{di +qi} and precision P_{di +qi} on all identifiers (micro-averaged over all annotators) as well as the three proposed evaluation metrics ER_di, ER_qi, and WP_{di +qi} from Section 6.