diff --git a/.gitattributes b/.gitattributes
index 60b77b54748b2e660dbb0ebac8e29f9e564fbbce..4d8d4c7972aed874c09371538db980b93c3bd987 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -342,3 +342,4 @@ data/AB/1950/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1976/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1977/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1975/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1989/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/f53447668acd4e7ab3838eeaf9677f3c_python.cwl b/.renku/workflow/f53447668acd4e7ab3838eeaf9677f3c_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..65b1b81c2d24a2ff0dc79186942420c0457c3ffd
--- /dev/null
+++ b/.renku/workflow/f53447668acd4e7ab3838eeaf9677f3c_python.cwl
@@ -0,0 +1,51 @@
+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_origxml.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/AB/1989/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1989/02_extractedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_3)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1989
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1989/02_extractedxml.tar.gz b/data/AB/1989/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..44b8ad4512042bbb2d2d3731c96e43bd6ef4e459
--- /dev/null
+++ b/data/AB/1989/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21088245a05f153dc5ed9a838526ac7866540b66ad6da156a57de8dee88e6e73
+size 361118864