Exploration and production data can be provided from one or more devices and categorized at a data lake system. The data lake system can include a temporary data repository where data is initially analyzed for determining whether the data includes data markers. Data markers can be correlated to existing data provided by the data lake system in order that tags can be generated for the incoming data. When data markers or other metadata is unavailable from the incoming data, the incoming data can be flagged for further processing to identify any available context that can be used as a basis for tagging.