The volatile nature of the global crop commodity market necessitates advanced analytical tools to enable stakeholders to make informed decisions based on timely and accurate data. However, the complex and diverse nature of agricultural data and crop commodities, often presented in unstructured formats, pose significant challenges in extracting meaningful insights.This paper examines the use of Large Language Models to enhance Named Entity Recognition techniques specifically designed for the crop commodity market. We investigate the efficacy of these models in effectively tagging and categorizing essential information such as agricultural products, vessel movements, and trade flows. Our findings suggest that while fine-tuned base models deliver high precision, LLMs like GPT-4 and Claude v2 offer comparable performance without the need for additional training on new entities.Nonetheless, deploying these advanced technologies raises issues concerning system reliability, robustness, and explainability. Addressing these challenges is crucial for maintaining the trustworthiness of NLP-powered systems in the crop commodity sector. This paper presents a preliminary design for increasing Trust in these automated systems.