EvalLLM 2026 · Entity Linking Challenge 🩺 Health surveillance

Entity Linking: knowing exactly what’s being talked about.

At the Entity Linking challenge of EvalLLM 2026, Kairntech ranked 1st in raw performance — linking every mention in health-surveillance bulletins to the correct official reference record, with a linking F1 of 89.98% (median 75.18%).

Organized by AMIAD · EvalLLM 2026 workshop & GT RAG (GdR TAL) — CORIA‑TALN, Nantes, 29 June 2026
1st
raw performance on the task
89.98%
best linking F1 — median 75.18%
3
systems submitted — 3 degrees of control
1,840
mentions to link across 200 documents
The task

Removing ambiguity.

Entity Linking links every mention in a text — a place, a disease, a pathogen… — to the correct record in an official reference database. That’s what lets you know exactly what, or where, is being referred to.

On French health-surveillance bulletins, the mentions were already spotted: the whole difficulty is the liage. Some mentions have no match at all (NIL cases), which is also an expected answer.

Technically

Resolution to GeoNames (places) and MeSH (biomedical), a cross-lingual task (FR text, English MeSH) where identifiers can be composite — D001906, D010930:M…, D1 & D2.

Biomedical mention in a bulletin
« botulism »
MeSH · D001906 — Botulism
Clostridium botulinum agent ≠ disease
Botulinum toxin BIO_TOXIN
The reference databases

Two official references.

GeoNames

The world’s reference geographic database: millions of places with their coordinates, countries and administrative divisions. In case of homonymy, the bulletin’s context decides — the same city name can exist in several countries.

MeSH

The reference medical thesaurus (diseases, pathogens, toxins…), in its French translation maintained by Inserm, complemented by NLM and NCBI concepts and codes for the finest identifiers.

Our approach

Three systems, three degrees of control.

The rules allowed three submissions: we used them to compare, on the same task, a continuum from procedural code to autonomous agent.

System 01

Gazetteer + LLM

Final decision by the LLM

Kairntech’s GeoNames and MeSH indexes propose candidates; a single LLM call decides based on context. The most integrated approach.

System 02

Pipeline Python

Framed sub-tasks · the most frugal

The code drives everything and calls the LLM only on targeted sub-tasks (translation, paraphrases, final choice). The best trade-off of performance / control / frugality.

System 03

Tool-equipped n8n agent

Agentic orchestration · best F1

An agent chooses which tools to call and reformulates its queries. Near-complete coverage (best F1), at the cost of much higher inference.

The results

Recall makes the difference.

Our two best systems clearly beat the challenge median. At comparable precision, everything comes down to couverture : the agent leaves barely 2.3% of mentions unlinked.

Kairntech ranks 1st in raw performance; the final ranking then applies frugality criteria that reshuffle the deck — and keep us on the podium.

System (linking F1)F1
n8n agent89.98%
Pipeline Python86.69%
Gazetteer + LLM74.49%
Median (19 runs)75.18%

Official results on 200 test documents · 7 teams · 19 runs. 1st in raw performance; final ranking after weighting by frugality criteria.

Precision — and frugality

We measured cost alongside quality. The agent gets the best F1 but consumes nearly twelve times more tokens than the pipeline for just 3.3 points gained. The Python pipeline stays the most frugal and controllable. Frugality — open-source, CO₂ footprint, compute resources — is a criterion we take seriously, and a direction we keep exploring.

Poster + Article

Get our Entity Linking resources

Our poster and detailed article from the Entity Linking challenge of EvalLLM 2026: GeoNames & MeSH databases, our 3 systems, results and carbon footprint. Leave your email — we’ll send you everything. (Documents currently available in French only.)

100% secure data
Free — no commitment
Instant access

The same precision, working on your data.

Structure and disambiguate your unstructured content with our entity extraction and linking pipelines.

© Kairntech · EvalLLM 2026 — Entity Linking Challenge · AMIAD, French Ministry of the Armed Forces