Knowledge graphs and ontologies form the backbone of structured, machine-readable knowledge representation, yet ontology terms often lack natural language descriptions, limiting their accessibility and reuse. Existing ontology verbalization approaches tend to rely on rule-based or template-driven techniques that operate on strict, formal schema axioms, resulting in rigid verbalizations that fail to convey richer contextual semantics. We present OntoDoc, a multi-agent framework for automatically generating natural language descriptions for any Internationalized Resource Identifier (IRI) within a SPARQL endpoint or RDF file. OntoDoc operates through a four-stage pipeline: (1) a Database Context agent that adaptively explores the knowledge graph via SPARQL to collect semantically informative triples about the target IRI; (2) a Web Context agent that retrieves and re-ranks encyclopedic background knowledge from Wikipedia and the open web; (3) an Assumption Generation agent that synthesizes both contexts into a structured, evidence-grounded list of intermediate assumptions; and (4) a Description Generation agent that produces the final natural language description from the grounded assumptions. We evaluate OntoDoc on three knowledge graphs spanning biomedical, agricultural, and cross-domain settings, using both automatic scoring via Large Language Models (LLMs) and human evaluation with 11 annotators. OntoDoc consistently matches or exceeds a naive LLM baseline and a template-based ontology verbalizer in accuracy. Furthermore, it vastly outperforms both baselines in the completeness of the generated descriptions, delivering an average 12% improvement in completeness over the naive baseline across all domains, and improving completeness scores by as much as 2.8 points on a 5-point scale relative to the ontology verbalizer.
Figures & tables
Figure 1: OntoDoc System Overview
Tool
Description
get_iri_information
Retrieves rdf:type, rdfs:label, rdfs:comment, dcterms:description, and skos:definition; also checks whether the IRI is used as a predicate.
get_outgoing_triples
Returns triples where the IRI is subject ( ⟨iri⟩?p?o ), max 200.
get_incoming_triples
Returns triples where the IRI is object ( ?s?p⟨iri⟩ ), max 200.
get_predicate_usage
For property IRIs, returns sample triples ( ?s⟨iri⟩?o ) and distinct rdf:type values of subjects and objects.
execute_sparql
Executes SPARQL SELECT/ASK queries with filtering, grouping, aggregation, and arbitrary patterns.
Table 1: Agent toolset for ontology exploration and SPARQL querying.
Assumption
Reasoning
LacrosseLeague is a class representing organized sports leagues specifically for the sport of lacrosse.
The IRI is typed as an OWL Class, specifically a subclass of SportsLeague , indicating that it represents a type of sports league focused on lacrosse. This is directly stated in triples 1 and 3.
LacrosseLeague is an internationally recognized concept describing leagues, associations, or organizations where lacrosse teams compete.
Multiple labels in different languages such as ‘lacrosse league’, ‘lacrosse bond’, ‘Lacrosse-Liga’ and others indicate the concept is universally recognized as a lacrosse sporting league entity. This is supported by triples 3–9.
…
Table 2: Extracted assumptions and reasonings for dbo:LacrosseLeague
Model
Win Rate (w/ assumptions)
Win Rate (w/o assumptions)
gpt-4.1-mini
47.02%
47.68%
gemini-2.5-flash-lite
23.18%
19.21%
glm-4.7-flash
29.80%
33.11%
Table 3: Win Rates with and without Assumptions
Knowledge Graph
Sample Size (n)
Assumptions Step Win Rate
DBpedia
30
57.00%
BioBricks-MeSH
51
61.00%
SOCKG
70
54.00%
Table 4: Assumptions Step Win Rate per Knowledge Graph for gpt-4.1-mini
Knowledge Graph
Metric
OntoDoc
Naive
DBpedia (n=30)
Accuracy
4.20
4.30
Clarity
4.47
4.73
Completeness
3.97
3.67
Cruciality
3.90
4.43
BioBricks-MeSH (n=51)
Accuracy
3.76
3.65
Clarity
4.43
4.24
Table 5: OntoDoc vs Naive Scores per Knowledge Graph
Knowledge Graph
Metric
Naive
OntoDoc
Verbalizer
DBpedia
Accuracy
4.20
4.30
1.50
Clarity
4.80
4.70
1.00
Completeness
3.40
4.00
1.20
Cruciality
4.50
4.10
1.50
BioBricks-MeSH
Accuracy
3.65
4.00
3.41
Clarity
4.24
4.71
3.94
Table 6: Rubric Scores (common URIs) per Knowledge Graph
KG
Accuracy
Clarity
Completeness
Cruciality
DBpedia
4.43
4.36
4.36
4.20
BioBricks-MeSH
4.51
4.49
4.43
4.34
SOCKG
3.93
3.65
3.72
3.74
Table 7: Average Human Annotation Scores by Knowledge Graph
Score
Label
Description
1
Poor
There are no accurate statements about the term. All the claims that are present in the description are factually incorrect.
2
Fair
The description contains at least one accurate statement, but one or more clearly incorrect claims are also present.
3
Good
All statements are plausibly accurate, but at least one is imprecise, overgeneralized, or weakly supported by the available evidence.
4
Very Good
All statements are accurate and reasonably precise, with only minor ambiguities in phrasing that do not mislead the reader.
5
Excellent
All statements are factually correct and expressed with full precision. There are no misleading, ambiguous, or unsupported claims.
Table 8: Accuracy Scoring Rubric
Score
Label
Description
1
Poor
The description is largely incomprehensible and the reader cannot extract a coherent meaning from it.
2
Fair
The description is difficult enough to follow that it requires significant effort to infer the core meaning.
3
Good
The core meaning is accessible, but at least one sentence or phrase is notably ambiguous or awkwardly constructed.
4
Very Good
The description is generally clear and easy to read, with only minor phrasing issues that do not impede understanding.
5
Excellent
The description is completely clear, fluent, and unambiguous throughout.
Table 9: Clarity Scoring Rubric
Score
Label
Description
1
Poor
The description covers only a superficial aspect of the concept and most essential information is absent.
2
Fair
The description covers some essential information but is missing one or more details that are critical to understanding the concept.
3
Good
The description covers the core of the concept adequately, but omits at least one secondary detail that would be expected in an ideal description of the term.
4
Very Good
The description covers all essential information needed to understand the concept, but omits secondary details that would further enrich it.
5
Excellent
The description covers all essential information and relevant secondary details, giving a full and representative picture of the concept.
Table 10: Completeness Scoring Rubric
Score
Label
Description
1
Poor
The description is dominated by off-topic or irrelevant content and appears to address a different concept entirely.
2
Fair
It is clear that the right concept is being described, but multiple non-essential details are present that significantly dilute the focus.
3
Good
The description is mostly about the right concept, but includes at least one tangential or redundant detail that adds noise without aiding understanding.
4
Very Good
The description is well-focused with at most one minor unnecessary detail that does not materially harm the overall description.
5
Excellent
Every included detail is essential toward understanding the concept, and nothing is superfluous.
Graph-based retrieval-augmented generation depends on the quality of the knowledge graph (KG) it retrieves over, yet schema-free LLM-based extraction pipelines typically produce flat graphs: deduplicated entities and relations with no type hierarchy and no domain/range constraints. We present AutoOntic, a pipeline that automatically constructs an ontology from text by canonicalizing open-vocabulary entity types and relations, inducing a hierarchy over the canonicalized types, and mining relation-level domain and range constraints. Its hierarchy induction procedure prioritizes types using corpus-derived relation-argument profiles and places them through local, LLM-adjudicated parent/child checks, allowing newly inserted types to trigger reassignment of existing parent-child links. The resulting hierarchy constrains entity deduplication and supports the induction of relation-level domain/range constraints. For intrinsic evaluation, we introduce a reference-based protocol that classifies induced ontology types as exact, broader, narrower, or unrelated to reference domain and range classes. On the Wikidata-TekGen and DBpedia-WebNLG subsets of Text2KGBench, over 90% of AutoOntic's induced endpoint types are semantically aligned with the reference classes across two LLM backbones: about half match exactly, while most remaining differences concern granularity. On MINE, knowledge graphs organized using an ontology built by AutoOntic achieve 88% retrieval accuracy. AutoOntic is available at https://github.com/screemix/AutoOntic.
Alla Chepurova, Aydar Bulatov, Mikhail Burtsev +1
Cognitive AI Systems Lab, Moscow, Russia · London Institute for Mathematical Sciences, London, UK
Ontology documentation, visualization, and validation are usually carried out with separate tools. This split workflow slows down development and makes knowledge transfer harder. We present OntoInk, an open-source MkDocs plugin that brings these activities together. Within a single documentation-as-code pipeline, OntoInk renders interactive ontology diagrams, validates instance data against SHACL shapes, runs OWL,DL reasoning, and supports inline Turtle editing. General-purpose diagram plugins for MkDocs cannot parse RDF, dereference IRIs, overlay SHACL constraints, or run OWL reasoning. Compared with standalone ontology visualization tools, OntoInk embeds interactive and editable diagrams directly into documentation pages. A live demo and source code are available at https://ise-fizkarlsruhe.github.io/ontoink/.
Ebrahim Norouzi, Jörg Waitelonis, Harald Sack
FIZ Karlsruhe – Leibniz Institute for Information Infrastructure, Germany · Karlsruhe Institute of Technology (KIT), Institute AIFB, Germany
Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured queries on the metadata. We show that when domain vocabulary and semantics are captured in a well-designed Web Ontology Language (OWL) ontology, Large Language Models (LLMs) can generate accurate structured queries zero-shot, without task-specific fine-tuning, retrieval augmentation, or multi-agent orchestration. We present the Natural Language Knowledge Graph Query (NLKGQ) system, a framework and development process that enables natural language access to metadata in such archives. The framework includes a web interface that helps researchers pose natural language questions, which a domain-agnostic harness translates to SPARQL via an LLM and executes against a knowledge graph. The development process begins with capturing domain vocabulary and semantics in a formal OWL ontology. Domain-specific code then extracts metadata from archive sources and imports it into a knowledge graph defined by the ontology. Both are designed for reuse across domains. We demonstrate the system on metadata derived from a large-scale neuroimaging research archive, evaluating multiple LLMs and ontology representations. The best configurations achieve 100% accuracy on a 21-question competency and regression test set developed with domain experts. An ablation study across eight ontology representations reveals that readable entity names and semantic annotations are the dominant factors in accuracy, more significant than model choice or prompt engineering. We also compare SPARQL to an auto-generated SQL database as query backends, showing that OWL's structural features provide a substantial advantage over SQL DDL for LLM-driven query generation. Our demonstration domain requires local LLMs on modest institutional hardware to address privacy concerns for human subject data.
Blake G. Fitch, Cato Elia Kurtz
Max Planck Institute for Biological Cybernetics Tübingen, Germany