U.S. Semantic Technologies Symposium Series
Details about Session 6, chaired by Dean Rehberger and Walter Hawthorne:
The discipline of history stands at a peculiar crossroads. Large language models now generate plausible-sounding narratives about the past with alarming fluency. Yet, they do so without genuine comprehension of causation, context, or the intricate web of evidence that undergirds historical interpretation. Meanwhile, historians possess centuries of methodological rigor for evaluating sources, tracing provenance, and constructing arguments from fragmentary evidence—precisely the kind of structured reasoning that semantic technologies were designed to formalize and make explicit.
This session explores how knowledge graphs, ontologies, and linked data can serve as critical infrastructure for historically-grounded AI systems. We examine practical challenges historians face when working with AI tools: how do we represent historical uncertainty and contested interpretations in formal semantic structures? Can we build open, reusable ontologies that capture the temporal complexity of historical entities—nations that cease to exist, individuals who change names, places that shift boundaries? What does explainable AI mean when the “ground truth” itself remains subject to scholarly debate?
Through a combination of short presentations and structured discussion, we will address the technical and epistemological dimensions of this challenge. Participants will examine case studies ranging from a digital project Mark Twain’s daily life to linked data approaches for tracking the Atlantic slave trade. They will explore how semantic technologies can make AI systems more transparent, verifiable, and aligned with the evidentiary standards that historical scholarship demands. The goal is not merely to apply existing technologies to historical problems, but to consider how history’s methodological sophistication might inform the next generation of explainable, trustworthy AI systems across domains.