Information extraction with LLMs is typically geared toward extracting individual subject-predicate-object (SPO) triples from short factual texts such as Wikipedia or news articles. In contrast, the L3X methodology tackles the task of extracting long lists from long texts: given a target subject S and predicate P, the goal is to extract the complete list of all objects O for which SPO holds. This is especially challenging over long texts, like entire books or large web crawls, where many objects are long-tail entities. We demonstrate L3X, a web-based system designed for this previously unexplored task. L3X comprises of recall-oriented candidate generation using LLMs in RAG mode, with novel methods for ranking and batching passages, followed by precision-oriented scrutinization. Our demo supports exploring multiple configurations, including LLM-only and RAG baselines, showcasing use cases like fiction-character relations from book series (e.g., 50+ friends of Harry Potter) and business relations from web pages (e.g., CEOs of Toyota).