{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:43:54Z","timestamp":1760060634403,"version":"build-2065373602"},"reference-count":32,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Structured knowledge representation is of great significance for constructing a knowledge graph of coal mine equipment safety. However, traditional methods encounter substantial difficulties when handling the complex semantics and domain-specific terms in technical texts. To tackle this challenge, we propose a knowledge extraction framework that integrates large language models (LLMs) with prompt engineering to achieve the efficient joint extraction of information. This framework strengthens the traditional triple structure by introducing symmetric entity-type information encompassing the head entity type and the tail entity type. Furthermore, it enables simultaneous entity recognition and relation extraction within a unified model. Experimental results demonstrate that the proposed knowledge extraction framework significantly outperforms the traditional step-by-step approach of first extracting entities and then relations. To meet the requirements of actual industrial production, we verified the impacts of different prompt strategies, as well as small lightweight models and large complex models, on the extraction task. Through multiple sets of comparative experiments, we found that the Chain-of-Thought (CoT) prompting strategy can effectively improve performance across different models, and the choice of model architecture has a significant impact on task performance. Our research provides an accurate and scalable solution for knowledge graph construction in the coal mine equipment safety domain, and its symmetry-aware design exhibits great potential for cross-domain knowledge transfer.<\/jats:p>","DOI":"10.3390\/sym17091490","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T08:40:15Z","timestamp":1757407215000},"page":"1490","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on Large Language Model-Based Automatic Knowledge Extraction for Coal Mine Equipment Safety"],"prefix":"10.3390","volume":"17","author":[{"given":"Ziheng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Management, China University of Mining and Technology (Beijing), Beijing 100083, China"}]},{"given":"Rijia","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Management, China University of Mining and Technology (Beijing), Beijing 100083, China"}]},{"given":"Yinhang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Heilongjiang University of Science and Technology, Harbin 150022, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6683-3272","authenticated-orcid":false,"given":"He","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Heilongjiang University of Science and Technology, Harbin 150022, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"key":"ref_1","first-page":"3269","article-title":"Statistical analysis and research on major and above coal mine accidents in China from 2011 to 2020","volume":"29","author":"Wang","year":"2023","journal-title":"J. Saf. Environ."},{"key":"ref_2","first-page":"101","article-title":"Analysis of the characteristics of China\u2019s mine accidents in the past five years and countermeasures for prevention and control","volume":"44","author":"Zhang","year":"2021","journal-title":"Coal Chem. Ind."},{"key":"ref_3","first-page":"175","article-title":"Application of fault diagnosis and early warning system in coal mining","volume":"49","author":"Zhang","year":"2021","journal-title":"Coal Sci. Technol."},{"key":"ref_4","first-page":"9","article-title":"Statistical analysis and countermeasures of major accidents in coal mines in China","volume":"34","author":"Wang","year":"2024","journal-title":"China Saf. Sci. J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1016\/j.psep.2021.07.032","article-title":"Construction and analysis of a coal mine accident causation network based on text mining","volume":"153","author":"Qiu","year":"2021","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_6","first-page":"76","article-title":"Construction of a mine accident knowledge graph based on Large Language Models","volume":"2","author":"Zhang","year":"2025","journal-title":"J. Mine Autom."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1418","DOI":"10.1038\/s41467-024-45563-x","article-title":"Structured information extraction from scientific text with large language models","volume":"15","author":"Dagdelen","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1812","DOI":"10.1093\/jamia\/ocad259","article-title":"Improving large language models for clinical named entity recognition via prompt engineering","volume":"31","author":"Hu","year":"2024","journal-title":"J. Am. Med Informatics Assoc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"102313","DOI":"10.1016\/j.datak.2024.102313","article-title":"To prompt or not to prompt: Navigating the use of large language models for integrating and modeling heterogeneous data","volume":"152","author":"Remadi","year":"2024","journal-title":"Data Knowl. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, C., Liu, X., Chen, Z., Hong, H., Tang, J., and Song, D. (2022). DeepStruct: Pretraining of language models for structure prediction. Findings ACL, 803\u2013823.","DOI":"10.18653\/v1\/2022.findings-acl.67"},{"key":"ref_11","unstructured":"Tang, X., Su, Q., Wang, J., and Deng, Z. (2024, January 20\u201325). Chisiec: An information extraction corpus for ancient chinese history. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, Torino, Italy."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"ocae095","DOI":"10.1093\/jamia\/ocae095","article-title":"Rt: A retrieving and chain-of-thought framework for few-shot medical named entity recognition","volume":"31","author":"Li","year":"2024","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"065012","DOI":"10.1088\/1674-4527\/ad3d15","article-title":"Astronomical knowledge entity extraction in astrophysics journal articles via large language models","volume":"24","author":"Shao","year":"2024","journal-title":"Res. Astron. Astrophys."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Meoni, S., Clergerie, D.L.E., and Ryffel, T. (2023, January 13). Large language models as instructors: A study on multilingual clinical entity extraction. Proceedings of the 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.bionlp-1.15"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Moassefi, M., Houshmand, S., Faghani, S., Chang, P.D., Sun, S.H., Khosravi, B., Triphati, A.G., Rasool, G., Bhatia, N.K., and Folio, L. (2025). Cross-institutional evaluation of large language models for radiology diagnosis extraction: A prompt-engineering perspective. J. Imaging Inform. Med.","DOI":"10.1007\/s10278-025-01523-5"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sasaki, Y., Washizaki, H., Li, J., Sander, D., Yoshioka, N., and Fukazawa, Y. (2024, January 2\u20134). Systematic literature review of prompt engineering patterns in software engineering. Proceedings of the 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC), Osaka, Japan.","DOI":"10.1109\/COMPSAC61105.2024.00096"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Chao, W., Qiu, Z., Zhu, H., and Xiong, H. (2024, January 13\u201317). Harnessing large language models for text-rich sequential recommendation. Proceedings of the ACM on Web Conference 2024, Singapore.","DOI":"10.1145\/3589334.3645358"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3713","DOI":"10.1007\/s11042-022-13428-4","article-title":"Natural language processing: State of the art, current trends and challenges","volume":"82","author":"Khurana","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100844","DOI":"10.1016\/j.websem.2024.100844","article-title":"Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective","volume":"85","author":"Lavrinovics","year":"2025","journal-title":"J. Web Semant."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Krupka, G. (1995, January 6\u20138). Description of the SRA system as used for MUC-6. Proceedings of the Sixth Message Understanding Conference (MUC-6), Columbia, MA, USA.","DOI":"10.3115\/1072399.1072419"},{"key":"ref_21","first-page":"46","article-title":"Research progress on named entity recognition in Chinese deep learning","volume":"59","author":"Li","year":"2023","journal-title":"Comput. Eng. Appl."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"15","DOI":"10.5121\/ijnlc.2012.1402","article-title":"Named entity recognition using hidden Markov model (HMM)","volume":"1","author":"Morwal","year":"2012","journal-title":"Int. J. Nat. Lang. Comput."},{"key":"ref_23","unstructured":"Chieu, H.L., and Ng, H.T. (September, January 24). Named entity recognition: A maximum entropy approach using global information. Proceedings of the 19th International Conference on Computational Linguistics, Taipei, Taiwan."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.eswa.2018.07.032","article-title":"Joint entity recognition and relation extraction as a multi-head selection problem","volume":"114","author":"Bekoulis","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.neucom.2016.12.075","article-title":"Joint entity and relation extraction based on a hybrid neural network","volume":"257","author":"Zheng","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_26","unstructured":"Isozaki, H., and Kazawa, H. (September, January 24). Efficient support vector classifiers for named entity recognition. Proceedings of the 19th International Conference on Computational Linguistics, Taipei, Taiwan."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"101712","DOI":"10.1016\/j.csl.2024.101712","article-title":"Adaptive feature extraction for entity relation extraction","volume":"89","author":"Yang","year":"2025","journal-title":"Comput. Speech Lang."},{"key":"ref_28","first-page":"1","article-title":"Deep mining the textual gold in relation extraction","volume":"58","author":"Sharma","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_29","first-page":"46","article-title":"Fault knowledge graph construction for coal mine fully mechanized mining equipment","volume":"49","author":"Cai","year":"2023","journal-title":"J. Mine Autom."},{"key":"ref_30","first-page":"49","article-title":"Coal mine safety: Knowledge graph construction and its QA approach","volume":"34","author":"Liu","year":"2020","journal-title":"J. Chin. Inf. Process."},{"key":"ref_31","first-page":"2866751","article-title":"A knowledge graph system for the maintenance of coal mine equipment","volume":"13","author":"Zhang","year":"2021","journal-title":"Math. Probl. Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3578938","article-title":"Efficient deep learning: A survey on making deep learning models smaller, faster, and better","volume":"55","author":"Menghani","year":"2023","journal-title":"ACM Comput. Surv."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/9\/1490\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:42:20Z","timestamp":1760035340000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/9\/1490"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"references-count":32,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["sym17091490"],"URL":"https:\/\/doi.org\/10.3390\/sym17091490","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,9,9]]}}}