{"id":"https://openalex.org/W7147622221","doi":"https://doi.org/10.48550/arxiv.2603.29878","title":"Performance Evaluation of LLMs in Automated RDF Knowledge Graph Generation","display_name":"Performance Evaluation of LLMs in Automated RDF Knowledge Graph Generation","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7147622221","doi":"https://doi.org/10.48550/arxiv.2603.29878"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29878","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.29878","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128100850","display_name":"Ioana  Ramona Martin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin, Ioana Ramona","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065947536","display_name":"Tudor Cioara","orcid":"https://orcid.org/0000-0003-1177-5795"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cioara, Tudor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019681375","display_name":"Ionu\u021b Anghel","orcid":"https://orcid.org/0000-0001-6166-5266"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anghel, Ionut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032076424","display_name":"Gabriel Ioan Arcas","orcid":"https://orcid.org/0009-0002-2246-5928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arcas, Gabriel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.4871000051498413,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.4871000051498413,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.10849999636411667,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.07739999890327454,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.7477999925613403},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6194999814033508},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5008999705314636},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked data","score":0.4812999963760376},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43160000443458557},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42899999022483826},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.3995000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820000052452087},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.7477999925613403},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6194999814033508},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.4812999963760376},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4237000048160553},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38609999418258667},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3314000070095062},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29878","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.29878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29878","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6542662382125854,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cloud":[0],"systems":[1],"generate":[2],"large,":[3],"heterogeneous":[4],"log":[5,88],"data":[6],"containing":[7],"critical":[8],"infrastructure,":[9],"application,":[10],"and":[11,30,70,100,118,125,147,171,179,203,210,223,230],"security":[12],"information.":[13],"Transforming":[14],"these":[15],"logs":[16,36,58,143],"into":[17,23],"RDF":[18,48,75,174,228],"triples":[19],"enables":[20],"their":[21,53],"integration":[22],"knowledge":[24,49],"graphs,":[25],"improving":[26],"interpretability,":[27],"root-cause":[28],"analysis,":[29],"cross-service":[31],"reasoning":[32],"beyond":[33],"what":[34],"raw":[35],"allow.":[37],"Large":[38],"Language":[39],"Models":[40],"(LLMs)":[41],"offer":[42],"a":[43,78,111,137,167,196],"promising":[44],"approach":[45],"to":[46,96,121,128],"automate":[47],"graph":[50],"generation;":[51],"however,":[52],"effectiveness":[54],"on":[55],"complex":[56],"cloud":[57],"remains":[59],"largely":[60],"unexplored.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,135],"evaluate":[66],"multiple":[67,94],"LLM":[68,235],"architectures":[69],"prompting":[71,194],"strategies":[72,205],"for":[73,84,226],"automated":[74],"extraction":[76,91,229],"using":[77,110,144],"controlled":[79],"framework":[80],"with":[81,115,164,187],"two":[82],"pipelines":[83],"systematically":[85],"processing":[86],"semi-structured":[87],"data.":[89],"The":[90],"pipeline":[92,114],"integrates":[93],"LLMs":[95],"identify":[97],"relevant":[98],"entities":[99],"relationships,":[101],"automatically":[102],"generating":[103],"subject-predicate-object":[104],"triples.":[105],"These":[106,215],"outputs":[107],"are":[108],"evaluated":[109],"dedicated":[112],"validation":[113],"both":[116],"syntactic":[117],"semantic":[119],"metrics":[120],"assess":[122],"accuracy,":[123],"completeness,":[124],"quality.":[126],"Due":[127],"the":[129,160,218],"lack":[130],"of":[131,220],"public":[132],"ground-truth":[133],"datasets,":[134],"created":[136],"reference":[138],"Log-to-KG":[139],"dataset":[140],"from":[141],"OpenStack":[142],"manual":[145],"annotation":[146],"ontology-driven":[148],"methods,":[149],"enabling":[150],"objective":[151],"baseline.":[152],"Our":[153],"analysis":[154],"shows":[155],"that":[156],"Few-Shot":[157,185],"learning":[158],"is":[159],"most":[161],"effective":[162,199],"strategy,":[163],"Llama":[165],"achieving":[166],"99.35%":[168],"F1":[169],"score":[170],"100%":[172],"valid":[173],"output":[175],"while":[176,201],"Qwen,":[177],"NuExtract,":[178],"Gemma":[180],"also":[181],"perform":[182,212],"well":[183],"under":[184],"prompting,":[186],"Chain-of-Thought":[188],"approaches":[189],"maintaining":[190],"similar":[191],"accuracy.":[192],"One-Shot":[193],"offers":[195],"lighter":[197],"but":[198],"alternative,":[200],"Zero-Shot":[202],"advanced":[204],"such":[206],"as":[207],"Tree-of-Thought,":[208],"Self-Critique,":[209],"Generate-Multiple":[211],"substantially":[213],"worse.":[214],"results":[216],"highlight":[217],"importance":[219],"contextual":[221],"examples":[222],"prompt":[224],"design":[225],"accurate":[227],"reveal":[231],"model-specific":[232],"limitations":[233],"across":[234],"architectures.":[236]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}