# Entity Resolution in Practice: Lessons from a Self-Serve Pipeline

arXiv: https://arxiv.org/abs/2607.26298 · HTML: https://mlsanity.com/paper/2607.26298/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 36 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [Entity Matching using Large Language Models](https://mlsanity.com/paper/2310.11244/) (2023)
- [ZeroER: Entity Resolution using Zero Labeled Examples](https://mlsanity.com/paper/1908.06049/) (2019)
- [(Almost) All of Entity Resolution](https://mlsanity.com/paper/2008.04443/) (2020)
- [Fine-tuning Large Language Models for Entity Matching](https://mlsanity.com/paper/2409.08185/) (2024)
- [Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration](https://mlsanity.com/paper/2312.03987/) (2023)
- [Agent-S: LLM Agentic workflow to automate Standard Operating Procedures](https://mlsanity.com/paper/2503.15520/) (2025)
- [Learning from Natural Language Explanations for Generalizable Entity Matching](https://mlsanity.com/paper/2406.09330/) (2024)
- [Exploiting Transitivity Constraints for Entity Matching in Knowledge Graphs](https://mlsanity.com/paper/2104.12589/) (2021)
- [Graph-based Active Learning for Entity Cluster Repair](https://mlsanity.com/paper/2401.14992/) (2024)
- [TransClean: Finding False Positives in Multi-Source Entity Matching under Real-World Conditions via Transitive Consistency](https://mlsanity.com/paper/2506.04006/) (2025)

## Abstract (arXiv)

We built and evaluated a self-serve entity resolution (ER) system on six benchmarks spanning 864 to 5M records, and three lessons emerged that are absent from existing ER literature. (1) No single matching algorithm wins everywhere - a self-serve pipeline cannot predict its next dataset, so we recommend training several algorithm families per dataset and letting an automatic bake-off pick the winner. (2) Precision and recall need separate fixes, not a shared threshold - precision needs hard rule-based vetoes, recall needs more diverse candidate retrieval. (3) One false-positive link can silently merge unrelated entities - assuming "A matches B" and "B matches C" implies "A matches C" lets a single bad link chain hundreds of records together, so every cross-group merge must be actively re-verified. We hope these lessons save practitioners the months of dead-end experiments that led us to them.