Large-scale biomedical entity recognition and relation extraction are essential foundational tasks for downstream text mining tasks and applications, such as knowledge graph construction. Because many relations span sentence boundaries, document-level entity recognition and relation extraction is closely aligned with real-world demands. However, identifying complex and diverse entities and relations within a limited timeframe is challenging. Therefore, we propose an end-to-end approach called BioECR for biomedical document-level named entity recognition, coreference resolution, and relation extraction. This approach utilizes a bi-encoder structure combined with biomedical entity types and descriptions to solve nested biomedical entities in linear time, thereby enhancing the ability to recognise complex entities and relations. Then a composition graph convolutional neural network was proposed to address the noise in conventional graph convolutional networks, thereby reducing time overhead and selectively fusing multiple entities or contextual information. Finally, by combining entity type clustering methods, the problem of coreference errors among multiple types of entities is solved easily and quickly. Experimental results demonstrate that our approach achieves stateof-the-art performance on all subtasks across three biomedical document-level datasets called CDR, GDA, and BioRED, and our approach reduces the inference time by approximately 60%.