From 0cdbf6f624ac8bc342a07f85ffa621f374093386 Mon Sep 17 00:00:00 2001
From: Christian Risi <75698846+CnF-Gris@users.noreply.github.com>
Date: Wed, 24 Sep 2025 16:15:47 +0200
Subject: [PATCH] Added query to retrieve a dirty dataset from SQLite DB

---
 Scripts/DatasetMerging/SQL_Queries/query.sql | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Scripts/DatasetMerging/SQL_Queries/query.sql b/Scripts/DatasetMerging/SQL_Queries/query.sql
index 150afce..2dc7f2a 100644
--- a/Scripts/DatasetMerging/SQL_Queries/query.sql
+++ b/Scripts/DatasetMerging/SQL_Queries/query.sql
@@ -43,3 +43,12 @@ INSERT INTO Subjects_Abbreviations(SubjectID, AbbreviationID) VALUES (?,?);
 -- Please be sure it is a URI before running this query
 --  and take at least until the domain and the first path part
 SELECT AbbreviationID FROM Abbreviations WHERE URI LIKE ?;
+
+-- Query to retrieve data
+SELECT MovieID, GROUP_CONCAT('<SOT>' || '<SUB>' || SubjectURI || '<REL>' || RelationshipURI || '<OBJ>' || ObjectURI || '<EOT>', '') as RDF_String, Abstract
+FROM RDFs
+INNER JOIN Subjects USING (SubjectID)
+INNER JOIN Relationships USING (RelationshipID)
+INNER JOIN Objects USING (ObjectID)
+INNER JOIN WikipediaAbstracts USING (MovieID)
+GROUP BY MovieID;