In the era of Generative AI, many data exploration systems still struggle to represent clear relationships between entities. This becomes important in biodiversity data, where species, taxonomy, occurrence records, countries, years, and record types are strongly connected.
In this session, the speaker will explore how Southeast Asian biodiversity occurrence data from the GBIF Occurrence API will be transformed into a Neo4j-based Knowledge Graph. The graph will connect entities such as Species, Genus, Family, Order, Class, Phylum, Kingdom, Occurrence, Country, Year, and Basis of Record. You will learn how to design a beginner-friendly graph schema, import biodiversity data into Neo4j, and use Cypher queries to analyze relationships such as species in the same family, occurrence records by country, and taxonomic classification paths. The session will also introduce GraphRAG and LLM-based Text-to-Cypher at a basic level, showing how graph context can support more structured and explainable answers.

This session will be aimed at students and beginner developers who want to apply Knowledge Graph concepts to real-world data. Through a practical demonstration, you will see how Neo4j, Cypher, and GraphRAG can turn biodiversity records into connected knowledge for graph analysis and AI-assisted question answering.