@inproceedings{cortes-2026-comparing,
title = "Comparing {LLM}-Based Knowledge Graph Extraction Approaches on Literary Studies in {S}panish: A Case Study on Orbis Tertius",
author = "Cortes, Federico",
editor = "Rehm, Georg and
Dietze, Stefan and
Dessi, Danilo and
Maynard, Diana and
Schimmler, Sonja",
booktitle = "Proceedings of Natural Scientific Language Processing ({NSLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nslp-1.8/",
doi = "10.63317/5kjis3dy8i7k",
pages = "78--87",
abstract = "Knowledge graph construction from scholarly text increasingly relies on large language models, yet different extraction architectures produce different graphs. Literary studies poses particular challenges: meaning is interpretive rather than factual, and the boundaries of relevant knowledge are determined by hermeneutic frameworks rather than empirical verification. We compare two LLM-based extraction frameworks{---}entity-anchored extraction (KGGen) and open extraction with schema canonicalization (EDC){---}on 472 Spanish-language literary studies articles from Orbis Tertius (1996{--}2024). Despite fundamental architectural differences, both methods converge on key findings: cultural framing dominates literary discourse by 2.2{--}2.5{\texttimes} over textual framing (p {\ensuremath{<}} .001), and core author networks remain consistent across approaches. The methods diverge in entity composition: KGGen captures more proper names (40.7{\%} vs. 18.7{\%}), while EDC captures more abstract concepts (42.8{\%}) and preserves Spanish predicates with 21,025 semantic definitions. Convergent findings across architecturally different methods merit higher confidence, and we identify methodological considerations for knowledge graph construction from humanities scholarship."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cortes-2026-comparing">
<titleInfo>
<title>Comparing LLM-Based Knowledge Graph Extraction Approaches on Literary Studies in Spanish: A Case Study on Orbis Tertius</title>
</titleInfo>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Cortes</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 Natural Scientific Language Processing (NSLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Dietze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Dessi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Maynard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</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>Knowledge graph construction from scholarly text increasingly relies on large language models, yet different extraction architectures produce different graphs. Literary studies poses particular challenges: meaning is interpretive rather than factual, and the boundaries of relevant knowledge are determined by hermeneutic frameworks rather than empirical verification. We compare two LLM-based extraction frameworks—entity-anchored extraction (KGGen) and open extraction with schema canonicalization (EDC)—on 472 Spanish-language literary studies articles from Orbis Tertius (1996–2024). Despite fundamental architectural differences, both methods converge on key findings: cultural framing dominates literary discourse by 2.2–2.5× over textual framing (p \ensuremath< .001), and core author networks remain consistent across approaches. The methods diverge in entity composition: KGGen captures more proper names (40.7% vs. 18.7%), while EDC captures more abstract concepts (42.8%) and preserves Spanish predicates with 21,025 semantic definitions. Convergent findings across architecturally different methods merit higher confidence, and we identify methodological considerations for knowledge graph construction from humanities scholarship.</abstract>
<identifier type="citekey">cortes-2026-comparing</identifier>
<identifier type="doi">10.63317/5kjis3dy8i7k</identifier>
<location>
<url>https://aclanthology.org/2026.nslp-1.8/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>78</start>
<end>87</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing LLM-Based Knowledge Graph Extraction Approaches on Literary Studies in Spanish: A Case Study on Orbis Tertius
%A Cortes, Federico
%Y Rehm, Georg
%Y Dietze, Stefan
%Y Dessi, Danilo
%Y Maynard, Diana
%Y Schimmler, Sonja
%S Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F cortes-2026-comparing
%X Knowledge graph construction from scholarly text increasingly relies on large language models, yet different extraction architectures produce different graphs. Literary studies poses particular challenges: meaning is interpretive rather than factual, and the boundaries of relevant knowledge are determined by hermeneutic frameworks rather than empirical verification. We compare two LLM-based extraction frameworks—entity-anchored extraction (KGGen) and open extraction with schema canonicalization (EDC)—on 472 Spanish-language literary studies articles from Orbis Tertius (1996–2024). Despite fundamental architectural differences, both methods converge on key findings: cultural framing dominates literary discourse by 2.2–2.5× over textual framing (p \ensuremath< .001), and core author networks remain consistent across approaches. The methods diverge in entity composition: KGGen captures more proper names (40.7% vs. 18.7%), while EDC captures more abstract concepts (42.8%) and preserves Spanish predicates with 21,025 semantic definitions. Convergent findings across architecturally different methods merit higher confidence, and we identify methodological considerations for knowledge graph construction from humanities scholarship.
%R 10.63317/5kjis3dy8i7k
%U https://aclanthology.org/2026.nslp-1.8/
%U https://doi.org/10.63317/5kjis3dy8i7k
%P 78-87
Markdown (Informal)
[Comparing LLM-Based Knowledge Graph Extraction Approaches on Literary Studies in Spanish: A Case Study on Orbis Tertius](https://aclanthology.org/2026.nslp-1.8/) (Cortes, NSLP 2026)
ACL