{"id":"https://openalex.org/W4396686373","doi":"https://doi.org/10.1145/3629527.3652900","title":"Building Massive Knowledge Graphs using an Automated ETL Pipeline","display_name":"Building Massive Knowledge Graphs using an Automated ETL Pipeline","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4396686373","doi":"https://doi.org/10.1145/3629527.3652900"},"language":"en","primary_location":{"id":"doi:10.1145/3629527.3652900","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629527.3652900","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3652900","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3652900","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006947708","display_name":"Aaron Eberhart","orcid":"https://orcid.org/0000-0003-3007-5460"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aaron Eberhart","raw_affiliation_strings":["metaphacts GmbH, Walldorf, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3007-5460","affiliations":[{"raw_affiliation_string":"metaphacts GmbH, Walldorf, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024067415","display_name":"Wolfgang Schell","orcid":"https://orcid.org/0009-0000-2909-1493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wolfgang Schell","raw_affiliation_strings":["metaphacts GmbH, Walldorf, Germany"],"raw_orcid":"https://orcid.org/0009-0000-2909-1493","affiliations":[{"raw_affiliation_string":"metaphacts GmbH, Walldorf, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015470269","display_name":"Peter Haase","orcid":"https://orcid.org/0000-0002-7561-7000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Haase","raw_affiliation_strings":["metaphacts GmbH, Walldorf, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7561-7000","affiliations":[{"raw_affiliation_string":"metaphacts GmbH, Walldorf, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006947708"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46904297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9976999759674072,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8193063735961914},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.6993291974067688},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6245567798614502},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5225788354873657},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4832044839859009},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.4675297737121582},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4299236536026001},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3653472363948822},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2864391505718231},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.27869102358818054},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23332160711288452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193063735961914},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.6993291974067688},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6245567798614502},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5225788354873657},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4832044839859009},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.4675297737121582},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4299236536026001},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3653472363948822},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2864391505718231},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27869102358818054},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23332160711288452}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3629527.3652900","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629527.3652900","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3652900","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3629527.3652900","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629527.3652900","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629527.3652900","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396686373.pdf"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4312406906","https://openalex.org/W6939432159"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W4319431024","https://openalex.org/W3001062969","https://openalex.org/W2054026175","https://openalex.org/W3115442681","https://openalex.org/W2391000461"],"abstract_inverted_index":{"Knowledge":[0],"graphs":[1,79],"are":[2,9,35],"extremely":[3],"versatile":[4],"semantic":[5],"tools,":[6],"but":[7],"there":[8],"current":[10],"bottlenecks":[11],"with":[12],"expanding":[13],"them":[14],"to":[15,43],"a":[16,22,45,56],"massive":[17,32,46],"scale.":[18],"This":[19],"concern":[20],"is":[21],"focus":[23],"of":[24,76],"the":[25,64,70,74,81],"Graph-Massivizer":[26,71],"project,":[27],"where":[28],"solutions":[29],"for":[30,84],"scalable":[31,59],"graph":[33,48],"processing":[34],"investigated.":[36],"In":[37],"this":[38],"paper":[39],"we'll":[40],"describe":[41],"how":[42,69],"build":[44],"knowledge":[47,78],"from":[49],"existing":[50],"information":[51],"or":[52],"external":[53],"sources":[54],"in":[55],"repeatable":[57],"and":[58,67,80],"manner.":[60],"We":[61],"go":[62],"through":[63],"process":[65],"step-by-step,":[66],"discuss":[68],"project":[72],"supports":[73],"development":[75],"large":[77],"considerations":[82],"necessary":[83],"replication.":[85]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}