28 seeds, one corroborated lead: an Epstein-network investigation in public data
What an entity-resolution pipeline finds (and misses) when pointed at 28 publicly-sourced seeds from the Epstein corporate-network reporting.
About
Ben Severn
Software engineer building open-source tools that make data quality accessible to every team.
I created the Golden Suite — a collection of Python libraries for checking, transforming, matching, and orchestrating data. Each tool works standalone or as part of the pipeline.
Current Projects
GoldenCheckData quality scanning
GoldenFlowData transformation
GoldenMatchEntity resolution & deduplication
GoldenPipePipeline orchestration
infermapSchema mapping engine
Open Source Data Tools
Open-source Golden Suite
Building tools that check, transform, match, and map data. All open source. All production-grade.
Projects
5 packages on PyPIRecent writing
All posts →Phoenix Spree Deutschland: one cluster from raw leak to GLEIF anchor
A 9-member ICIJ cluster, 100% GLEIF-anchored, walked from source rows through GoldenMatch dedupe to a finished provenance report.
Reconciling 4.1M shell-company records on a single Railway box
Ingesting ICIJ + GLEIF + OpenSanctions + UK PSC into one unified company table, then deduping it with GoldenMatch on a 24-vCPU Railway service.