KGpipe: Generation and Evaluation of Pipelines for Data Integration into Knowledge Graphs

TL;DR

KGpipe is a flexible framework that enables the creation and evaluation of end-to-end pipelines for integrating diverse data sources into knowledge graphs, supporting reproducibility and combining various tools and LLM functionalities.

Contribution

The paper introduces KGpipe, a novel framework for defining and executing reproducible data integration pipelines into knowledge graphs, including a benchmark for evaluation.

Findings

Demonstrated the flexibility of KGpipe with multiple pipeline configurations.

Evaluated different pipelines using performance and quality metrics.

Showcased integration of heterogeneous data formats into KGs.

Abstract

Building high-quality knowledge graphs (KGs) from diverse sources requires combining methods for information extraction, data transformation, ontology mapping, entity matching, and data fusion. Numerous methods and tools exist for each of these tasks, but support for combining them into reproducible and effective end-to-end pipelines is still lacking. We present a new framework, KGpipe for defining and executing integration pipelines that can combine existing tools or LLM (Large Language Model) functionality. To evaluate different pipelines and the resulting KGs, we propose a benchmark to integrate heterogeneous data of different formats (RDF, JSON, text) into a seed KG. We demonstrate the flexibility of KGpipe by running and comparatively evaluating several pipelines integrating sources of the same or different formats using selected performance and quality metrics.