Exploring a Large Language Model for Transforming Taxonomic Data into OWL: Lessons Learned and Implications for Ontology Development

TL;DR

This paper tackles the challenge of keeping taxonomic names up to date in agricultural ontologies, particularly within APTO. It compares two AI-driven workflows: a ChatGPT-4 BrowserOp approach for direct GBIF data extraction and OWL generation, and a Python-based Taxonomy OWLizer that scales to larger species lists while ensuring coherent taxon hierarchies. The study demonstrates that the BrowserOp method can be fast for small tests but suffers from scalability and reproducibility issues, whereas the Python-based approach delivers scalable and robust OWL output with careful handling of synonyms and hybrids, albeit with dependencies on external validation and pre-processing. The work highlights a practical, hybrid pathway for automating taxonomy integration in domain ontologies, informs best practices for future AI-assisted ontology engineering, and provides a reusable pipeline and web tool for broader biodiversity and agricultural data applications.

Abstract

Managing scientific names in ontologies that represent species taxonomies is challenging due to the ever-evolving nature of these taxonomies. Manually maintaining these names becomes increasingly difficult when dealing with thousands of scientific names. To address this issue, this paper investigates the use of ChatGPT-4 to automate the development of the :Organism module in the Agricultural Product Types Ontology (APTO) for species classification. Our methodology involved leveraging ChatGPT-4 to extract data from the GBIF Backbone API and generate OWL files for further integration in APTO. Two alternative approaches were explored: (1) issuing a series of prompts for ChatGPT-4 to execute tasks via the BrowserOP plugin and (2) directing ChatGPT-4 to design a Python algorithm to perform analogous tasks. Both approaches rely on a prompting method where we provide instructions, context, input data, and an output indicator. The first approach showed scalability limitations, while the second approach used the Python algorithm to overcome these challenges, but it struggled with typographical errors in data handling. This study highlights the potential of Large language models like ChatGPT-4 to streamline the management of species names in ontologies. Despite certain limitations, these tools offer promising advancements in automating taxonomy-related tasks and improving the efficiency of ontology development.

Figures (6)

• Figure 1: Example of synonym in Agrotermos in Portuguese.
• Figure 2: Workflow for the taxonomic data transformation.
• Figure 3: Duplicated labels and relationships in the ontology visualization in Protégé.
• Figure 4: Classes hierarchy in Protégé.
• Figure 5: 'Pimenta' and its translation as Black pepper in Wikipedia.