Grottes de Han - La Salle d'Armes: réapparition de la Lesse

closed Item 01KQHSJA8M147G3QWMA5T0PCAC cropped postcard
new triaged uploaded enriched extracted ▶ closed remove
Grottes de Han - La Salle d'Armes: réapparition de la Lesse
ARK
QR code for image 01KQHSM47S7DZX81MZCS70PNAJ
Name
2Dbcu8j9EotU36sboZxtZ6
https://n2t.net/ark:/11635/2Dbcu8j9EotU36sboZxtZ6
https://scanstation.ai/ark/11635/2Dbcu8j9EotU36sboZxtZ6
File
Order 12
Dimensions 7968 × 5984
Orientation 0
S3 Key marac/003/derivatives/0012.jpg
Source Path marac/003/derivatives/0012.jpg
AI Enrichment
Summary
Sepia postcard front showing the Grottes de Han cave interior with rocky walls, an underground river, and a small railed walkway or bridge; the printed French caption identifies the scene as 'La Salle d'Armes: réapparition de la Lesse' at Han-sur-Lesse, Belgium.
OCR Excerpt
Grottes de Han La Salte d Aruves ; réapparition de la Lesse
Places
Grottes de Han, Han-sur-Lesse, Belgium La Salle d'Armes cave chamber
Type
text_page document photo photo_with_text postcard
Tags
No tags assigned.
Primary: postcard
Searchable text 59 chars 1%

Grottes de Han La Salte d Aruves ; réapparition de la Lesse

ai-tools@1.0 Tesseract via ai-tools (12 words, mean conf 79.3)
Subject: image:01KQHSM47S7DZX81MZCS70PNAJ 17 predicates
Predicate Best value Conf. Source
ai:denseSummary
Sepia postcard front showing the Grottes de Han cave interior with rocky walls, an underground river, and a small railed walkway or bridge; the printed French caption identifies the scene as 'La Salle d'Armes: réapparition de la Lesse' at Han-sur-Lesse, Belgium.
1% enrich_from_thumbnail@1.0
ai:documentLikely yes
ai-tools heuristic on scan.storage:marac/003/0012.jpg
1% ai-tools@1.0
ai:handwrittenText
ai:hasText yes 1% enrich_from_thumbnail@1.0
ai:highResGoal
none
Little additional cataloging value would be lost beyond finer tonal/detail study of the cave scene.
1% enrich_from_thumbnail@1.0
ai:isFilledForm
ai:isForm
ai:ocrText
Grottes de Han La Salte d Aruves ; réapparition de la Lesse
Tesseract via ai-tools (12 words, mean conf 79.3)
1% ai-tools@1.0
ai:peopleLikely
ai:photoLikely yes
ai-tools heuristic on scan.storage:marac/003/0012.jpg
1% ai-tools@1.0
ai:photoWithTextLikely yes
ai-tools heuristic on scan.storage:marac/003/0012.jpg
1% ai-tools@1.0
ai:pixelsDone yes
Thumbnail clearly shows a postcard front with a short printed caption and the main scenic content; no small handwritten or dense printed text requiring high-resolution review is visible.
1% enrich_from_thumbnail@1.0
ai:speculation
This is likely a souvenir postcard intended for visitors to the Grottes de Han cave complex.
Printed caption strip, scenic composition, and named tourist site are typical features of souvenir postcards.
1% enrich_from_thumbnail@1.0
ai:typedText yes 1% enrich_from_thumbnail@1.0
dcterms:spatial
Grottes de Han, Han-sur-Lesse, Belgium La Salle d'Armes cave chamber
1% aggregated
dcterms:title
Grottes de Han - La Salle d'Armes: réapparition de la Lesse
1% enrich_from_thumbnail@1.0
dcterms:type
text_page
OCR detected multi-word text; OCR confidence suggests printed text
5% ai-tools@1.0
Subject: image:01KQHSM47S7DZX81MZCS70PNAJ 4 claims
This is likely a souvenir postcard intended for visitors to the Grottes de Han cave complex.?? Printed caption strip, scenic composition, and named tourist site are typical features of souvenir postcards. ai:speculation · 1%
The image likely depicts the reappearance of the underground river Lesse within the cave system.?? The printed caption explicitly says 'réapparition de la Lesse', and the scene shows water running through the cave chamber. ai:speculation · 1%
Grottes de Han, Han-sur-Lesse, Belgium?? Printed caption names 'Grottes de Han' and 'Lesse', identifying the cave site associated with Han-sur-Lesse in Belgium. dcterms:spatial · 1%
La Salle d'Armes cave chamber?? Printed caption explicitly identifies the depicted location as 'La Salle d'Armes'. dcterms:spatial · 1%
Subject: image:01KQHSM47S7DZX81MZCS70PNAJ 0 claims
No claims recorded yet for this subject.
closed — No more image calls. Item workflow consumes image claims/text/metadata for catalog-level analysis.
TransitionDescription
upload Pushes realPath (the ai-tools crop) to S3 as the canonical image. When defaults.full_frame_key is present, also archives the original mat under originals/ on S3 for re-processing / QR re-extraction during Python dev. The full-frame archive is planned to drop for real-client tenants.
external_upload Sets defaults["storage"]["mode"] = "external_url". Used by IIIF imports so the image remains accessible via its external URL and subsequent transitions can run against it directly. Skips triage — the UPLOADED place lets enrich run against the remote URL.
triage When fired from NEW: local-file mode. ai-tools reads defaults.full_frame_key + defaults.sidecar_key from the shared dir, produces the canonical crop + thumbnail in derivatives/, and returns deskew/type/detections. realPath is repointed at the crop. When re-run from TRIAGED: same, idempotent. Non-URL mode is the only path browser captures take. Failures keep the image in NEW (async retry).
enrich Single cheap AI call (~$0.0004) against a ≤512px thumbnail, with triage OCR + flags in context. Populates title/description/subjects/people/places/dense_summary and text-type flags. Can run from TRIAGED (using ssai image_view via imgProxy, skipping S3 upload) or from UPLOADED. Re-runnable from enriched for debugging.
extract The optional second image call. Runs only when enrich_from_thumbnail sets pixelsDone=false. Dispatches by extraction goal/signals: filled forms → ExtractMetadata; handwriting → TranscribeHandwriting; dense print/layout → OcrMistral. Re-runnable.
close Bookkeeping only. Requires pixelsDone=true. The item workflow performs text-only catalog analysis across all images. Apply
Subject: image:01KQHSM47S7DZX81MZCS70PNAJ 23 claims
enrich_from_thumbnail@1.0 14
Predicate Value Conf. Basis
ai:denseSummary
Sepia postcard front showing the Grottes de Han cave interior with rocky walls, an underground river, and a small railed walkway or bridge; the printed French caption identifies the scene as 'La Salle d'Armes: réapparition de la Lesse' at Han-sur-Lesse, Belgium.
1%
ai:handwrittenText
ai:hasText yes 1%
ai:highResGoal
none
1%
Little additional cataloging value would be lost beyond finer tonal/detail study of the cave scene.
ai:isFilledForm
ai:isForm
ai:pixelsDone yes 1%
Thumbnail clearly shows a postcard front with a short printed caption and the main scenic content; no small handwritten or dense printed text requiring high-resolution review is visible.
ai:speculation
This is likely a souvenir postcard intended for visitors to the Grottes de Han cave complex.
1%
Printed caption strip, scenic composition, and named tourist site are typical features of souvenir postcards.
ai:speculation
The image likely depicts the reappearance of the underground river Lesse within the cave system.
1%
The printed caption explicitly says 'réapparition de la Lesse', and the scene shows water running through the cave chamber.
ai:typedText yes 1%
dcterms:spatial Grottes de Han, Han-sur-Lesse, Belgium 1%
Printed caption names 'Grottes de Han' and 'Lesse', identifying the cave site associated with Han-sur-Lesse in Belgium.
dcterms:spatial La Salle d'Armes cave chamber 1%
Printed caption explicitly identifies the depicted location as 'La Salle d'Armes'.
dcterms:title
Grottes de Han - La Salle d'Armes: réapparition de la Lesse
1%
dcterms:type
postcard
1%
ai-tools@1.0 9
Predicate Value Conf. Basis
ai:documentLikely yes 1%
ai-tools heuristic on scan.storage:marac/003/0012.jpg
ai:hasText yes 1%
Tesseract via ai-tools (12 words, mean conf 79.3)
ai:peopleLikely
ai-tools heuristic on scan.storage:marac/003/0012.jpg
ai:photoLikely yes 1%
ai-tools heuristic on scan.storage:marac/003/0012.jpg
ai:photoWithTextLikely yes 1%
ai-tools heuristic on scan.storage:marac/003/0012.jpg
dcterms:type
text_page
5%
OCR detected multi-word text; OCR confidence suggests printed text
dcterms:type
document
4%
document outline covers 85% of frame; OCR suggests readable text
dcterms:type
photo
3%
colorfulness 34.8 looks photographic
dcterms:type
photo_with_text
3%
photo-like image with probable text regions