diff --git a/.gitattributes b/.gitattributes
index 60b77b54748b2e660dbb0ebac8e29f9e564fbbce..9de0b70826b32defd8cd5f3d1b243761f5523dfc 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/1985/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/e03a3f7482434e7994415e6b2bb3efaf_python.cwl b/.renku/workflow/e03a3f7482434e7994415e6b2bb3efaf_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..bcd67516abe22a7757ebcc64792e7c2db918ce64
--- /dev/null
+++ b/.renku/workflow/e03a3f7482434e7994415e6b2bb3efaf_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/1985/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1985/02_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/1985
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1985/02_extractedxml.tar.gz b/data/AB/1985/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..87c2be4b6ce7c6f493028c71b1e81f361f8afd7b
--- /dev/null
+++ b/data/AB/1985/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fb241217ab239ef59f2e66fc885b1087c4f34a4b7b654402ac5cf641cf6842
+size 345827555