diff --git a/.gitattributes b/.gitattributes
index 18ee830be1a5b51eca58f6dda667870c3e9b6f03..d544dc1716f4948f29c55f48ee766cfb3ae8b031 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -2,3 +2,4 @@ data/AB/*/*tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1891/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1892/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1893/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1891/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/5d9113bd3e2c4a109fdb2b91acddef69_python.cwl b/.renku/workflow/5d9113bd3e2c4a109fdb2b91acddef69_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..6fe0cfc6d2cc6537ab845e3a869a6f181fd8e6c3
--- /dev/null
+++ b/.renku/workflow/5d9113bd3e2c4a109fdb2b91acddef69_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/1891/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1891/02_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/1891
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1891/02_extractedxml.tar.gz b/data/AB/1891/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..6e68262b753d30ac54486b1d51f8f21b34f6d3d6
--- /dev/null
+++ b/data/AB/1891/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:408b299adff3e39a3d195b486f89c8bfcf6a85ffb91a30256d559cd79b599b8b
+size 43120412