Reconstructing temporal multi-relational firm networks at scale using large language models. The case of the semiconductor industry

2026-05-15

AI Summary

This study addresses the challenge of capturing the dynamic complexity of global multi-relational corporate networks in the semiconductor industry, which traditional proprietary databases—often costly and lagging—struggle to track in a timely manner. The authors propose a generalizable framework that leverages large language models to automatically extract and classify supply chain, collaboration, and ownership relationships from 170 million open web pages, constructing a time-series multi-relational network encompassing over 1,300 firms. Integrating web crawling, natural language processing, and graph analytics, the approach enables high-tempo, automated structuring of relational data, achieving a precision of 0.884 and an F1 score of 0.784 in link extraction. Empirical analysis reveals network contraction during the 2022 chip shortage, a sharp rise in centrality among AI-critical firms, and geographically reconfigured ties driven by geopolitical forces.

Abstract

The semiconductor industry is foundational to modern technology, yet its complex global multi-relational firm network remains poorly understood, posing challenges to scientists, firms, and policymakers. Traditional analysis relies on proprietary databases that are often expensive, incomplete, and slowly updated, limiting their ability to capture rapidly evolving dependencies. Here, we demonstrate that a novel, generalizable methodology combining Large Language Models (LLMs) with open web data can reconstruct this network and its structural dynamics at scale. We identify and classify supply-chain, partnership, and ownership links from 170 million semiconductor firm webpages, yielding a temporal network of over 1,300 linked firms. We validate link-extraction quality (Precision: 0.884; F1-score: 0.784), network overlap and complementarity with a proprietary database, and consistency with aggregate economic data. Our network reveals a temporary 9% decline in edges during the 2022 chip shortage, rapid increases in the centrality of AI supply-chain bottleneck firms such as NVIDIA, and geographic realignment of interfirm relations amid geopolitical turbulence. This generalizable framework overcomes barriers to transparency and provides essential, up-to-date maps for assessing resilience and informing policy across strategically relevant sectors.

Problem

• firm networks
• semiconductor industry
• multi-relational
• temporal dynamics
• supply-chain

Innovation

• Large Language Models
• Temporal Multi-relational Networks
• Open Web Data
• Supply Chain Reconstruction
• Semiconductor Industry