Give RAG cleaner evidence before retrieval starts

The Experiment
We tested this idea using the Leipzig English News corpora from the Wortschatz Project at Leipzig University. We analyzed datasets from 2023, 2024 and 2025.

Across these datasets, the pipeline processed roughly:

2 million raw news articles
400K articles after topical filtering
From these documents the pipeline extracted:

millions of entity mentions
tens of millions of co-mention relationships
To focus on economic and technology narratives, documents were filtered using the IPTC Media Topics taxonomy, keeping only:

Economy, Business and Finance
Science and Technology

Large Language Models are powerful systems for language generation and reasoning.
However, when they are used for entity extraction in enterprise environments, they introduce instability where reliability is required.
Entity extraction is not about creativity or interpretation. It is infrastructure. In production systems, entities must be extracted in a way that is consistent, repeatable, and stable over time.

Tagging consistency is essential to ensure that training is smooth. Contradictions and inconsistencies not only decrease accuracy but also generate hidden costs in MLOps when trying to debug and fix errors. We often take this consistency for granted, but that is rarely the case, not only in these datasets but also in any other manual tagging work.

Consistency starts with having a solid and clear definition of what an entity is. Typically, if not always, that’s not the case.

And knowledge graphs are built using automatic data extraction tools: not only entity extraction but also concept extraction and relationships among entities or concepts.

German and Korean do not break retrieval because they are unusually complex; they break retrieval because most systems still treat complex words as monolithic strings. When compounds and eojeols remain opaque, search engines cannot align queries with documents—even when they contain the same meaning. Any team building multilingual search, vector search or RAG must incorporate reliable decompounding as a foundational step to avoid systematic retrieval failures.

Tagging consistency is essential to ensure that training is smooth. Contradictions and inconsistencies not only decrease accuracy but also generate hidden costs in MLOps when trying to debug and fix errors. We often take this consistency for granted, but that is rarely the case, not only in these datasets but also in any other manual tagging work.

Consistency starts with having a solid and clear definition of what an entity is. Typically, if not always, that’s not the case.

And knowledge graphs are built using automatic data extraction tools: not only entity extraction but also concept extraction and relationships among entities or concepts.

Problem. There’s broad consensus today: LLMs are phenomenal personal productivity tools — they draft, summarize, and assist effortlessly.
But there’s also growing recognition that they’re still not ready for enterprise-grade deployment.

Rationale. NER tools are at the heart of how the scientific community is solving LLM issues using GraphRAG and NodeRAG architectures.

LLMs need knowledge graphs to control hallucinations and make them more solid for enterprise-level use.

And knowledge graphs are built using automatic data extraction tools: not only entity extraction but also concept extraction and relationships among entities or concepts.

As described in our previous post “Using Public Corpora to Build Your NER systems”, we are going to highlight areas where public datasets like OntoNotes or CoNLL can be improved. We will provide some tips on how to avoid these issues, whenever possible, using (semi-)automatic techniques.

Tagging consistency is essential to ensure that training is smooth. Contradictions and inconsistencies not only decrease accuracy but also generate hidden costs in MLOps when trying to debug and fix errors. We often take this consistency for granted, but that is rarely the case, not only in these datasets but also in any other manual tagging work.

Consistency starts with having a solid and clear definition of what an entity is. Typically, if not always, that’s not the case.

And knowledge graphs are built using automatic data extraction tools: not only entity extraction but also concept extraction and relationships among entities or concepts.

The new Forrester Wave™: Data Governance Solutions, Q3 2025 makes one thing clear: governance is no longer about static catalogs. Vendors are moving fast into Active Metadata and Agentic AI, with features like lineage, observability, policy enforcement, and marketplaces for data assets.

The process of building Knowledge Graphs is essential for organizations seeking to organize, structure, and extract actionable insights from their data. However, traditional methods of constructing Knowledge Graphs are often slow, expensive, and complex, requiring significant expertise and manual effort. Bitext NAMER changes the game by automating key steps in the Knowledge Graph creation process, making it faster, more cost-effective, and accessible for businesses of all sizes.

In the era of data-driven decision-making, Knowledge Graphs (KGs) have emerged as pivotal tools for structuring, organizing, and interconnecting vast amounts of information. From enhancing search engine capabilities to powering AI-driven insights, KGs rely heavily on extracting, interpreting, and linking data elements with precision. At the core of this process lies Named Entity Recognition (NER), event extraction, and relationship mapping, foundational technologies for enabling robust knowledge management. Bitext’s NER solution, NAMER, is uniquely positioned to support the growing needs of KG companies, offering unparalleled features that address common industry challenges.

Verticalizing AI21’s Jamba 1.5 with Bitext Synthetic Text

Efficiency and Benefits of Verticalizing LLMs – The Case of Jamba 1.5 Mini.