Data Overdose? Time for a Quadruple Shot: Knowledge Graph Construction using Enhanced Triple Extraction
Authors:
- Taine J. ElliottTETaine J. Elliott
- Stephen P. LevittSLStephen P. Levitt
- Ken NixonKNKen Nixon
- Martin BekkerMBMartin Bekker
Preprint
Abstract
The rapid expansion of publicly-available medical data presents a challenge for clinicians and researchers alike, increasing the gap between the volume of scientific literature and its applications. The steady growth of studies and findings overwhelms medical professionals at large, hindering their ability to systematically review and understand the latest knowledge. This paper presents an approach to information extraction and automatic knowledge graph (KG) generation to identify and connect biomedical knowledge. Through a pipeline of large language model (LLM) agents, the system decomposes 44 PubMed abstracts into semantically meaningful proposition sentences and extracts KG triples from these sentences. The triples are enhanced using a combination of open domain and ontology-based information extraction methodologies to incorporate ontological categories. On top of this, a context variable is included during extraction to allow the triple to stand on its own - thereby becoming `quadruples'. The extraction accuracy of the LLM is validated by comparing natural language sentences generated from the enhanced triples to the original propositions, achieving an average cosine similarity of 0.874. The similarity for generated sentences of enhanced triples were compared with generated sentences of ordinary triples showing an increase as a result of the context variable. Furthermore, this research explores the ability for LLMs to infer new relationships and connect clusters in the knowledge base of the knowledge graph. This approach leads the way to provide medical practitioners with a centralised, updated in real-time, and sustainable knowledge source, and may be the foundation of similar gains in a wide variety of fields.Keywords
All Related Versions
- Version 1, 2025-08-05, ArXiv
- Published version: , 224.
This publication has 16 references indexed in Scilit:
- Accelerating Medical Knowledge Discovery Through Automated Knowledge Graph Generation and Enrichment2025
- Large language models for generative information extraction: a surveyFrontiers of Computer Science, 2024
- Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Text2023
- Knowledge enhanced LSTM for coreference resolution on biomedical textsBioinformatics, 2021
- BioBERT: a pre-trained biomedical language representation model for biomedical text miningBioinformatics, 2019
- Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reportsJournal of Biomedical Informatics, 2012
- Coreference resolution: A review of general methodologies and applications in the clinical domainJournal of Biomedical Informatics, 2011
- The Unified Medical Language System (UMLS): integrating biomedical terminologyNucleic Acids Research, 2004
- The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical textJournal of Biomedical Informatics, 2003
- Relationships in Medical Subject Headings (MeSH)2001