Largescale Complex Question Answering Dataset


LC-QuAD is a Question Answering dataset with 5000 pairs of question and its corresponding SPARQL query. The target knowledge base is DBpedia, specifically, the April, 2016 version. Please see our paper for details about the dataset creation process and framework.


Rank System Precision Recall F1 Score
1 QAmp
Vienna University of Economics and Business, Austria
0.25 0.50 0.33
2 WDAqua
Université de Lyon, France
0.22 0.38 0.28
- Krantikari QA
Smart Data Analytics, Germany
Paper | Code
* We're in the process of automating the benchmarking process, to populate the leaderboard. In the meantime, please get in touch with us at to add your entry here, and we'll do it manually.


  • Find the train and test splits here.
  • Use DBpedia v04-16 to benchmark your system on LC-QuAD. Here's a guide on setting up your own endpoint.
  • We're in the process of creating a one-click benchmarking process. For the time being, please contact us to report your results
Every data item in the dataset consists of the following fields:

sparql_template_id: "Every unique SPARQL template has a different ID.",
sparql_query: "Valid SPARQL queries.",
intermediary_question: "The automatically verbalized equivalent of the SPARQL Query.",
corrected_question: "Human corrected version of the verbalized question.",
_id: "Unique ID of the datapoint"
v0.1.3 - 21-06-2018
  • Published train, test splits
  • Updated Webpage
  • Dataset now hosted on Github as opposed to the Fighsare Project
v0.1.2 - 24-01-2018
  • Dataset now available in QALD format
  • Leaderboard underway!
v0.1.1 - 27-10-2017
  • [BUGFIX] Fixed a typo with rdf:type in the SPARQLs
  • Updated Datasets and Templates list.
v0.1.0 - 01-05-2017
  • [RELEASE] First version of the dataset released with 5000 datapoints.
  • published
title={Lc-quad: A corpus for complex question answering over knowledge graphs},
author={Trivedi, Priyansh and Maheshwari, Gaurav and Dubey, Mohnish and Lehmann, Jens},
booktitle={Proceedings of the 16th International Semantic Web Conference (ISWC)},