This paper presents a multi-pipeline Japanese-to-English machine translation (MT) system designed to address the challenge of translating repeated elements from Japanese into fluent and lexically diverse English. The system is developed as part of the Non-Repetitive Translation Task at WMT24, which focuses on minimizing redundancy while maintaining high translation quality. Our approach utilizes MeCab, the de facto NLP tool for Japanese, for the identification of repeated elements, and Claude Sonnet 3.5, a large language model (LLM), for translation and proofreading. The system effectively accomplishes the shared task by identifying and translating in a diversified manner 89.79% of the 470 repeated instances in the testing dataset, and achieving an average translation quality score of 4.60 out of 5, significantly surpassing the baseline score of 3.88. Analysis also revealed the challenges encountered, particularly in identifying standalone noun-suffix elements and occasional cases of consistent translations or mistranslations.