Diagnosing the state of charge, state of health, or state of power of a Lithium-ion battery (LIB) has been a key focus in battery research for many years. However, with a growing demand for circular reusage and recycling especially of automotive traction batteries, a new issue arises: Often, there is no secured knowledge about the cell chemistry upon entering the second life or afterlife stage of the battery. Not only for assessing feasible second life applications but also for evaluating possible recycling treatments, this knowledge is inevitable for recycling companies. In this work, we present a machine learning based approach for identifying cathode chemistries for LIBs. First, the determination of the measurement boundary conditions is introduced. To create training data, a single particle model from the Python Battery Mathematical Modelling Framework (PyBaMM) was used to create synthetical partial open circuit voltage (OCV) charge and discharge curves for three different cathode chemistries. The initial state of charge and state of health values as well as the initial capacities were varied to ensure a better generalization. The dV/dQ characteristics were selected as features and four different machine learning algorithms were trained on different OCV curve lengths. Determination of the trade-off between achievable accuracy and number of OCV steps showed a correlation between an increasing accuracy and a higher step number. While extremely small charge and discharge capacities per step did not yield sufficient testing accuracies, capacities starting from 0.2 Ah per step up to 0.6 Ah per step showed increasingly good results with an accuracy of up to 89.3% for 0.5 Ah and 15 OCV steps. Additionally, the approach was validated by classifying experimental data. The results particularly demonstrate the effectiveness to distinguish between lithium iron phosphate and lithium nickel manganese cobalt cells, which is an economically vital aspect for recycling companies and potential second life applications. An accuracy of 86.5% with only 5 OCV steps was reached for this case.