Large Language Models (LLMs) have demonstrated promise in transforming theways that individuals synthesis and interact with large amounts of information.However, current LLMs are limited in their ability to provide explanations aboutcausal relationships in data. In this paper, we investigate the ability of LLMsto answer queries related to causal relationships within time series data. Wegenerate synthetic datasets based on three distinct directed acyclic graphs (DAGs)representing causal relationships among time series variables. Initially, we useabstract variable names in the analysis and later assign real-world meanings tothese variables to align with the DAG structures. Using in-context learning, wepresent the relationships of these variables to the LLM in the prompt and evaluatehow effectively the LLMs identify the variables that caused specific observationsin an outcome variable.