Abstract

The growing volume and complexity of legal texts highlight the need for automatic methods capable of extracting structured information from unstructured documents. Motivated by the limited availability and high cost of annotated legal data, this challenge is even more severe for the Portuguese language. This work investigates whether prompt engineering over Large Language Models (LLMs) can effectively support legal Named Entity Recognition (NER) in low-supervision and low-resource settings through In-Context Learning (ICL). Using the LeNER-Br corpus, we evaluate category-specific prompts, different chunking sizes, and prompt engineering strategies. Entity-level evaluation using Exact Match Micro F1 shows that prompt engineering has a stronger impact on performance than other strategies. The best results were obtained with larger models, the 4-bit quantised Qwen-2.5:32B and GPT-5.2, achieving scores of 57.9% and 71.9%, respectively, highlighting the potential of this approach as an alternative to traditional supervised NER pipelines.