Aligning unstructured climate policy documents according to a particular classification taxonomy with little to no labeled examples is challenging and requires manual effort of climate policy researchers. In this work we examine whether large language models (LLMs) can act as an effective substitute or assist in the annotation process. Utilizing a large set of text spans from Paris Agreement Nationally Determined Contributions (NDCs) linked to United Nations Sustainable Development Goals (SDGs) and targets contained in the Climate Watch dataset from the World Resources Institute in combination with our own annotated data, we validate our approaches and establish a benchmark for model performance evaluation on this task. With our evaluation benchmarking we quantify the effectiveness of using zero-shot or few-shot prompted LLMs to align these documents.