Tower Bridge, London
new
→
triaged
→
uploaded
→
enriched
→
extracted
→
▶ closed
→
remove
Tower Bridge, London
ARK
Name
2DbctpgR4bNosLinzMWXrX
https://n2t.net/ark:/11635/2DbctpgR4bNosLinzMWXrX
https://scanstation.ai/ark/11635/2DbctpgR4bNosLinzMWXrX
File
| Order | 9 |
|---|---|
| Dimensions | 7968 × 5984 |
| Orientation | 0 |
| S3 Key | marac/003/derivatives/0009.jpg |
| Source Path | marac/003/derivatives/0009.jpg |
AI Enrichment
Summary
Color postcard front showing Tower Bridge in London with its bascules raised over the River Thames, small boats in the foreground, and the printed caption 'Tower Bridge, London' at top.
OCR Excerpt
LONDON
+
ev
.
1
A
.
Eee
BB,
a
w
Uy
a
14
a
ax
ws
3
fe)
K
Places
Tower Bridge, London, England
Type
text_page
document
photo
people_photo
photo_with_text
postcard
Tags
No tags assigned.
Primary: postcard
Searchable text
55 chars
0%
LONDON + ev . 1 A . Eee BB, a w Uy a 14 a ax ws 3 fe) K
ai-tools@1.0
Tesseract via ai-tools (20 words, mean conf 45.8)
Subject: image:01KQHSCN51BRAZ07DAZCN62QN1
17 predicates
| Predicate | Best value | Conf. | Source |
|---|---|---|---|
| ai:denseSummary |
Color postcard front showing Tower Bridge in London with its bascules raised over the River Thames, small boats in the foreground, and the printed caption 'Tower Bridge, London' at top.
|
1% | enrich_from_thumbnail@1.0 |
| ai:documentLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0009.jpg
|
1% | ai-tools@1.0 |
| ai:handwrittenText | |||
| ai:hasText | yes | 1% | enrich_from_thumbnail@1.0 |
| ai:highResGoal |
none
Minimal; only minor printing and color-process details would be missed, not core searchable content.
|
1% | enrich_from_thumbnail@1.0 |
| ai:isFilledForm | |||
| ai:isForm | |||
| ai:ocrText |
LONDON
+
ev
.
1
A
.
Eee
BB,
a
w
Uy
a
14
a
ax
ws
3
fe)
K
Tesseract via ai-tools (20 words, mean conf 45.8)
|
0% | ai-tools@1.0 |
| ai:peopleLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0009.jpg
|
1% | ai-tools@1.0 |
| ai:photoLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0009.jpg
|
1% | ai-tools@1.0 |
| ai:photoWithTextLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0009.jpg
|
1% | ai-tools@1.0 |
| ai:pixelsDone |
yes
Thumbnail clearly shows a postcard front with a short readable printed caption and no small handwritten or dense textual content requiring high-resolution review.
|
1% | enrich_from_thumbnail@1.0 |
| ai:speculation |
This is likely a souvenir postcard intended for visitors or collectors of London landmarks.
Front-facing scenic landmark image with printed location caption and postcard-style border matches common souvenir postcard design.
|
1% | enrich_from_thumbnail@1.0 |
| ai:typedText | yes | 1% | enrich_from_thumbnail@1.0 |
| dcterms:spatial |
Tower Bridge, London, England
|
1% | aggregated |
| dcterms:title |
Tower Bridge, London
|
1% | enrich_from_thumbnail@1.0 |
| dcterms:type |
document
document outline covers 85% of frame; OCR suggests readable text
|
4% | ai-tools@1.0 |
Subject: image:01KQHSCN51BRAZ07DAZCN62QN1
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.
| Transition | Description | |
|---|---|---|
| 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:01KQHSCN51BRAZ07DAZCN62QN1
23 claims
enrich_from_thumbnail@1.0
13
| Predicate | Value | Conf. | Basis |
|---|---|---|---|
| ai:denseSummary |
Color postcard front showing Tower Bridge in London with its bascules raised over the River Thames, small boats in the foreground, and the printed caption 'Tower Bridge, London' at top.
|
1% | — |
| ai:handwrittenText | — | ||
| ai:hasText | yes | 1% | — |
| ai:highResGoal |
none
|
1% |
Minimal; only minor printing and color-process details would be missed, not core searchable content.
|
| ai:isFilledForm | — | ||
| ai:isForm | — | ||
| ai:pixelsDone | yes | 1% |
Thumbnail clearly shows a postcard front with a short readable printed caption and no small handwritten or dense textual content requiring high-resolution review.
|
| ai:speculation |
This is likely a souvenir postcard intended for visitors or collectors of London landmarks.
|
1% |
Front-facing scenic landmark image with printed location caption and postcard-style border matches common souvenir postcard design.
|
| ai:speculation |
The image likely depicts Tower Bridge opening to allow river traffic to pass.
|
1% |
The bridge bascules are visibly raised and vessels are present on the water.
|
| ai:typedText | yes | 1% | — |
| dcterms:spatial | Tower Bridge, London, England | 1% |
Landmark is clearly depicted and confirmed by the printed caption 'TOWER BRIDGE. LONDON.'
|
| dcterms:title |
Tower Bridge, London
|
1% | — |
| dcterms:type |
postcard
|
1% | — |
ai-tools@1.0
10
| Predicate | Value | Conf. | Basis |
|---|---|---|---|
| ai:documentLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0009.jpg
|
| ai:hasText | yes | 1% |
Tesseract via ai-tools (20 words, mean conf 45.8)
|
| ai:peopleLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0009.jpg
|
| ai:photoLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0009.jpg
|
| ai:photoWithTextLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0009.jpg
|
| dcterms:type |
text_page
|
2% |
OCR detected multi-word text
|
| dcterms:type |
document
|
4% |
document outline covers 85% of frame; OCR suggests readable text
|
| dcterms:type |
photo
|
4% |
person detector suggests a photo; colorfulness 18.6 looks photographic
|
| dcterms:type |
people_photo
|
3% |
found 2 person-like region(s)
|
| dcterms:type |
photo_with_text
|
3% |
photo-like image with probable text regions
|