Few-shot Named Entity Recognition (Few-shot NER) aims to identify and classify unseen named entity types with a limited labeled samples. In recent years, large language models have achieved remarkable results in various NLP tasks due to their excellent zero/few-shot generalization capabilities. Recent research has extensively focused on using large language models to study the named entity recognition task. Negative sample entities have been demonstrated to be effective when performing this task using in-context learning paradigm. However, the problem of low efficiency and poor quality in manually constructing negative sample entities has been exposed. To address this issue, in this paper, we propose a Few-shot NER method based on generative negative sample enhancement (GNSE). Specifically, GNSE first utilizes a large language model to pre-identify potential entity spans in the support set text paragraphs in a zero-shot manner and generate the semantics of the spans based on the paragraph context. Then, the pre-identified candidate spans are compared with the ground-truth labels to determine positive or negative sample entity spans. Finally, based on Chain-of-Thought, the span semantics, positive and negative sample entities, and ground-truth labels are inserted into the example template for the in-context learning paradigm, and the test text from the query set is concatenated to construct a complete prompt. GNSE was evaluated on three widely used datasets: CoNLL’03, WNUT’17 and GUM. Experiments show that GNSE has achieved better performance.