{"id":28372520,"url":"https://github.com/eccenca/ck25-dataset","last_synced_at":"2025-10-13T07:32:26.134Z","repository":{"id":291724413,"uuid":"978554982","full_name":"eccenca/ck25-dataset","owner":"eccenca","description":"The CK25 Corporate Knowledge Reference Dataset for Benchmarking Text 2 SPARQL Question Answering Approaches","archived":false,"fork":false,"pushed_at":"2025-05-19T09:39:59.000Z","size":493,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-06-20T21:41:06.924Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc-by-4.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/eccenca.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-06T07:00:43.000Z","updated_at":"2025-05-19T09:20:05.000Z","dependencies_parsed_at":"2025-05-06T08:36:18.410Z","dependency_job_id":"ff35bc2c-113d-4e79-9725-f9f68d196049","html_url":"https://github.com/eccenca/ck25-dataset","commit_stats":null,"previous_names":["eccenca/ck25-dataset"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/eccenca/ck25-dataset","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eccenca%2Fck25-dataset","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eccenca%2Fck25-dataset/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eccenca%2Fck25-dataset/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eccenca%2Fck25-dataset/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eccenca","download_url":"https://codeload.github.com/eccenca/ck25-dataset/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eccenca%2Fck25-dataset/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279014119,"owners_count":26085463,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-13T02:00:06.723Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-05-29T15:42:03.228Z","updated_at":"2025-10-13T07:32:26.122Z","avatar_url":"https://github.com/eccenca.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003c!-- markdownlint-disable MD012 MD013 MD024 MD033 --\u003e\n# The CK25 Corporate Knowledge Reference Dataset for Benchmarking Text 2 SPARQL Question Answering Approaches\n\nText to SPARQL is a task that aims to automatically generate SPARQL queries which retrieve answers from RDF-based Knowledge Graphs.\nAs pointed out in [Strappazon  et al.](https://hal.science/hal-04918564) ...\n\n\u003e ... the task of parsing natural language questions into structured queries is even more prevalent now, given the high potential that Large Language Models (LLMs) offer in Retrieval-Augmented conversational agents and the problems they face with using the correct information as context.\n\nIn order to support researchers of RAG-based systems with reference questions and queries for a Knowledge Graph with an industrial background, we provide this dataset repository, which was created for the [First International TEXT2SPARQL Challenge](https://text2sparql.aksw.org/), which we organized as part of the [4th International Workshop on LLM-Integrated Knowledge Graph Generation from Text (Text2KG)](https://aiisc.ai/text2kg2025) at the [22th European Semantic Web Conference (ESWC2025)](https://2025.eswc-conferences.org/).\n\n## Important Files\n\n- `questions.yml`\n  - This YAML file is the curated list of 50 questions together with a working reference SAPRQL query\n- `graphs/`\n  - This directory contains Turtle files (one for the ontology, one for the instance data)\n  - The `*.graph` files contain the named graph IRI we use\n\n## How to use this repository?\n\nIn order to test your own Text to SPARQL approach, provide it as a TEXT2SPARQL endpoint as described [here](https://text2sparql.aksw.org/challenge/#process).\nThen you can use the [text2sparql](https://pypi.org/project/text2sparql-client/) command line client like this:\n\n``` shell-session\n$ text2sparql ask questions.yml [YOUR ENDPOINT] --output result.json\n2025-05-05 09:47:45.049 | INFO     | text2sparql_client.commands.ask:ask_command:72 - Asking questions about dataset https://text2sparql.aksw.org/2025/corporate/ on endpoint [YOUR ENDPOINT].\n2025-05-05 09:47:45.049 | INFO     | text2sparql_client.commands.ask:ask_command:77 - In which department is Ms. Brant? (en) ...\n2025-05-05 09:47:45.064 | INFO     | text2sparql_client.commands.ask:ask_command:77 - What is the telephone of Baldwin Dirksen? (en) ...\n2025-05-05 09:47:45.069 | INFO     | text2sparql_client.commands.ask:ask_command:77 - Who is the manager of Heinrich Hoch? (en) ...\n... more questions\n2025-05-05 09:49:43.421 | INFO     | text2sparql_client.commands.ask:ask_command:100 - Writing 50 responses to result.json.\n```\n\nThe new file result.json contains a structure like this:\n\n``` JSON\n[\n  {\n    \"dataset\": \"https://text2sparql.aksw.org/2025/corporate/\",\n    \"question\": \"In which department is Ms. Brant?\",\n    \"query\": \"...\",\n    \"endpoint\": \"[YOUR ENDPOINT]\",\n    \"qname\": \"ck25:1-en\",\n    \"uri\": \"https://text2sparql.aksw.org/2025/corporate/1-en\"\n  },\n...\n]\n```\n\nThis file can be used with the same CLI for analysis:\n\n\n``` shell-session\n$ text2sparql evaluate API_NAME questions.yml result.json\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feccenca%2Fck25-dataset","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feccenca%2Fck25-dataset","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feccenca%2Fck25-dataset/lists"}