The scientific method
We like to drop any of the scientific principles to fast forward an opinion or a project.
Most knowledge graphs are built like press releases, not data science. An LLM reads a document, extracts stuff, writes it to the graph, done. No hypothesis, no test, no error bar, no way to be wrong later. That’s not knowledge engineering, it’s more like stenography. The scientific method has four habits that KG pipelines routinely skip.
Hypothesis. A claim is a hypothesis, not a fact. Every extracted triple should carry a credence instead of a checkmark. “Confident” and “true” are different properties.
Provenance. If you can’t trace a triple back to the observation that produced it, you can’t replicate it, audit it, or revise it. A graph without provenance isn’t a knowledge base, it’s a rumor with good formatting.
Falsifiability, not permanence. Science doesn’t delete superseded results, it supersedes them with a timestamp and a reason. Most graphs still treat every assertion as eternally true the moment it’s ingested.
Reproducibility. Replication is the real validation step. If two independent passes over the same source produce different triples with no accounting for why, you don’t have an extraction pipeline, you have a random generator with a schema.
None of this is exotic really. It’s just what every first-year STEM student is trained to do (to understand, to acknowledge). Why do we silently forget when we move into business?