I am building a knowledge graph using BAML [baml-py] to extract documents [it's opinionated towards docs] and then PySpark to ETL the data into a node / edge list. GPT4o got few relations... Gemini 2.5 got so many it was nuts, all accurate but not all from the article! I had to reign it in and instruct it not to build so vast a graph. Really cool, it knows a LOT about semiconductors :)