Mineral named entity recognition (MNER) is the extraction for the specific types of entities from unstructured Chinese mineral text, which is a prerequisite for building a mineral knowledge graph. MNER can also provide important data support for the work related to mineral resources. Chinese mineral text has many types of entities, complex semantics, and a large number of rare characters. To extract entities from Chinese mineral literature, this paper proposes an MNER model based on deep learning. To create word embeddings for mineral text, Bidirectional Encoder Representations from Transformers (BERT) is used. Moreover, the transfer matrix of the Conditional Random Field (CRF) algorithm is combined to improve the accuracy of sequence labeling. Finally, some experiments are conducted on the constructed dataset. The results show that the model can effectively recognize seven mineral entities with an average F1-score of 0.842.