@inproceedings{simonsen-etal-2026-entity,
title = "Entity Linking for {F}aroese Using Large Language Models with Web Search",
author = "Simonsen, Annika and
Debess, Iben Nyholm and
Einarsson, Hafsteinn",
editor = "Morger, Felix and
Ilinykh, Nikolai and
Scalvini, Barbara and
Dobnik, Simon and
Dann{\'e}lls, Dana",
booktitle = "Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models ({RESOURCEFUL} 2026)",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.resourceful-4.4/",
doi = "10.63317/2myt23gboqw3",
pages = "32--43",
abstract = "Entity linking connects text mentions to knowledge bases. For low-resource languages, entity linking has typically not been a research priority, as named entity recognition and knowledge base creation must first be addressed. We present the first study of entity linking for Faroese, a North Germanic language with approximately 70,000 speakers. Unlike traditional systems that rely on separate candidate retrieval and ranking components, we employ an end-to-end approach using GPT-5 with integrated web search. Our method prompts the model to directly identify and link named entities to Wikipedia pages through a three-tier fallback strategy: Faroese Wikipedia, English Wikipedia, and finally any available Wikipedia. We evaluate our approach on 1,010 manually annotated examples from a Faroese NER dataset, analyzing entity mentions across Person, Location, Organization, and Miscellaneous types. Human evaluation shows our system achieves 87.5{\%} precision and 87.3{\%} recall, with particularly strong performance on locations (93-95{\%} precision, 92-95{\%} recall). Persons are more challenging (86-88{\%} precision, 72-83{\%} recall). The majority of links (76.5{\%}) point to Faroese Wikipedia, demonstrating the model{'}s ability to leverage language-specific knowledge bases. A Wikipedia API search baseline without any LLM achieves F1 = 0.57{--}0.60 on the same evaluation data, confirming that the LLM{'}s contextual reasoning provides substantial gains over simple search. We validate our approach across three models (GPT-5, Gemini{~}3 Flash, GPT-5.4{~}Mini), achieving F1 scores of 0.74{--}0.87 and confirming that the method generalizes across providers. This work establishes initial performance benchmarks for Faroese entity linking and demonstrates the viability of LLM-based approaches for low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simonsen-etal-2026-entity">
<titleInfo>
<title>Entity Linking for Faroese Using Large Language Models with Web Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annika</namePart>
<namePart type="family">Simonsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iben</namePart>
<namePart type="given">Nyholm</namePart>
<namePart type="family">Debess</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hafsteinn</namePart>
<namePart type="family">Einarsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Morger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Dannélls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Entity linking connects text mentions to knowledge bases. For low-resource languages, entity linking has typically not been a research priority, as named entity recognition and knowledge base creation must first be addressed. We present the first study of entity linking for Faroese, a North Germanic language with approximately 70,000 speakers. Unlike traditional systems that rely on separate candidate retrieval and ranking components, we employ an end-to-end approach using GPT-5 with integrated web search. Our method prompts the model to directly identify and link named entities to Wikipedia pages through a three-tier fallback strategy: Faroese Wikipedia, English Wikipedia, and finally any available Wikipedia. We evaluate our approach on 1,010 manually annotated examples from a Faroese NER dataset, analyzing entity mentions across Person, Location, Organization, and Miscellaneous types. Human evaluation shows our system achieves 87.5% precision and 87.3% recall, with particularly strong performance on locations (93-95% precision, 92-95% recall). Persons are more challenging (86-88% precision, 72-83% recall). The majority of links (76.5%) point to Faroese Wikipedia, demonstrating the model’s ability to leverage language-specific knowledge bases. A Wikipedia API search baseline without any LLM achieves F1 = 0.57–0.60 on the same evaluation data, confirming that the LLM’s contextual reasoning provides substantial gains over simple search. We validate our approach across three models (GPT-5, Gemini 3 Flash, GPT-5.4 Mini), achieving F1 scores of 0.74–0.87 and confirming that the method generalizes across providers. This work establishes initial performance benchmarks for Faroese entity linking and demonstrates the viability of LLM-based approaches for low-resource languages.</abstract>
<identifier type="citekey">simonsen-etal-2026-entity</identifier>
<identifier type="doi">10.63317/2myt23gboqw3</identifier>
<location>
<url>https://aclanthology.org/2026.resourceful-4.4/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>32</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity Linking for Faroese Using Large Language Models with Web Search
%A Simonsen, Annika
%A Debess, Iben Nyholm
%A Einarsson, Hafsteinn
%Y Morger, Felix
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Dobnik, Simon
%Y Dannélls, Dana
%S Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F simonsen-etal-2026-entity
%X Entity linking connects text mentions to knowledge bases. For low-resource languages, entity linking has typically not been a research priority, as named entity recognition and knowledge base creation must first be addressed. We present the first study of entity linking for Faroese, a North Germanic language with approximately 70,000 speakers. Unlike traditional systems that rely on separate candidate retrieval and ranking components, we employ an end-to-end approach using GPT-5 with integrated web search. Our method prompts the model to directly identify and link named entities to Wikipedia pages through a three-tier fallback strategy: Faroese Wikipedia, English Wikipedia, and finally any available Wikipedia. We evaluate our approach on 1,010 manually annotated examples from a Faroese NER dataset, analyzing entity mentions across Person, Location, Organization, and Miscellaneous types. Human evaluation shows our system achieves 87.5% precision and 87.3% recall, with particularly strong performance on locations (93-95% precision, 92-95% recall). Persons are more challenging (86-88% precision, 72-83% recall). The majority of links (76.5%) point to Faroese Wikipedia, demonstrating the model’s ability to leverage language-specific knowledge bases. A Wikipedia API search baseline without any LLM achieves F1 = 0.57–0.60 on the same evaluation data, confirming that the LLM’s contextual reasoning provides substantial gains over simple search. We validate our approach across three models (GPT-5, Gemini 3 Flash, GPT-5.4 Mini), achieving F1 scores of 0.74–0.87 and confirming that the method generalizes across providers. This work establishes initial performance benchmarks for Faroese entity linking and demonstrates the viability of LLM-based approaches for low-resource languages.
%R 10.63317/2myt23gboqw3
%U https://aclanthology.org/2026.resourceful-4.4/
%U https://doi.org/10.63317/2myt23gboqw3
%P 32-43
Markdown (Informal)
[Entity Linking for Faroese Using Large Language Models with Web Search](https://aclanthology.org/2026.resourceful-4.4/) (Simonsen et al., RESOURCEFUL 2026)
ACL