0043.jpg
new
→
triaged
→
uploaded
→
enriched
→
extracted
→
▶ closed
→
remove
0043.jpg
ARK
Name
2DbdG_BEWYRcYXjEvRdKPw
https://n2t.net/ark:/11635/2DbdG_BEWYRcYXjEvRdKPw
https://scanstation.ai/ark/11635/2DbdG_BEWYRcYXjEvRdKPw
File
| Order | 43 |
|---|---|
| Dimensions | 7968 × 5984 |
| Orientation | 0 |
| S3 Key | marac/003/derivatives/0043.jpg |
| Source Path | marac/003/derivatives/0043.jpg |
AI Enrichment
Summary
Color photographic image of a small temple-like stone ruin with several freestanding columns set in a rocky mountain landscape, likely depicting an ancient archaeological site in a Mediterranean setting.
Places
mountain archaeological site
Type
people_photo
photo
photo_with_text
text_present
photograph
Tags
No tags assigned.
Primary: photograph
No description yet.
Subject: image:01KQJA18JTCM6TJGEN1ZN56TT3
16 predicates
| Predicate | Best value | Conf. | Source |
|---|---|---|---|
| ai:denseSummary |
Color photographic image of a small temple-like stone ruin with several freestanding columns set in a rocky mountain landscape, likely depicting an ancient archaeological site in a Mediterranean setting.
|
1% | enrich_from_thumbnail@1.0 |
| ai:documentLikely | |||
| ai:handwrittenText | |||
| ai:hasText | |||
| ai:highResGoal |
none
Some finer architectural detail and exact site identification may remain uncertain, but no obvious text or form data would be lost.
|
1% | enrich_from_thumbnail@1.0 |
| ai:isFilledForm | |||
| ai:isForm | |||
| ai:ocrText |
Tesseract via ai-tools (0 words, mean conf 95.0)
|
1% | ai-tools@1.0 |
| ai:peopleLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0043.jpg
|
1% | ai-tools@1.0 |
| ai:photoLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0043.jpg
|
1% | ai-tools@1.0 |
| ai:photoWithTextLikely |
yes
ai-tools heuristic on scan.storage:marac/003/0043.jpg
|
1% | ai-tools@1.0 |
| ai:pixelsDone |
yes
Thumbnail is sufficient to identify the scene as a color view of ancient stone columns in a mountainous landscape; no legible text or small critical details are visible.
|
1% | enrich_from_thumbnail@1.0 |
| ai:speculation |
The image likely depicts the remains of an ancient temple or sanctuary rather than a modern structure.
The standing cylindrical columns with simple capitals and broken entablature are characteristic of excavated monumental ruins.
|
1% | enrich_from_thumbnail@1.0 |
| ai:typedText | |||
| dcterms:spatial |
mountain archaeological site
|
1% | aggregated |
| dcterms:type |
people_photo
found 1 face(s)
|
5% | ai-tools@1.0 |
Subject: image:01KQJA18JTCM6TJGEN1ZN56TT3
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:01KQJA18JTCM6TJGEN1ZN56TT3
21 claims
enrich_from_thumbnail@1.0
12
| Predicate | Value | Conf. | Basis |
|---|---|---|---|
| ai:denseSummary |
Color photographic image of a small temple-like stone ruin with several freestanding columns set in a rocky mountain landscape, likely depicting an ancient archaeological site in a Mediterranean setting.
|
1% | — |
| ai:handwrittenText | — | ||
| ai:hasText | — | ||
| ai:highResGoal |
none
|
1% |
Some finer architectural detail and exact site identification may remain uncertain, but no obvious text or form data would be lost.
|
| ai:isFilledForm | — | ||
| ai:isForm | — | ||
| ai:pixelsDone | yes | 1% |
Thumbnail is sufficient to identify the scene as a color view of ancient stone columns in a mountainous landscape; no legible text or small critical details are visible.
|
| ai:speculation |
The image likely depicts the remains of an ancient temple or sanctuary rather than a modern structure.
|
1% |
The standing cylindrical columns with simple capitals and broken entablature are characteristic of excavated monumental ruins.
|
| ai:speculation |
The scene may be in Greece or another eastern Mediterranean region.
|
0% |
The combination of classical-looking ruins, dry grass, and rocky mountains suggests a Mediterranean archaeological landscape, but no identifying inscription or landmark is visible.
|
| ai:typedText | — | ||
| dcterms:spatial | mountain archaeological site | 1% |
Ancient-looking stone columns are shown in an open mountainous landscape; no more specific location is legible.
|
| dcterms:type |
photograph
|
1% | — |
ai-tools@1.0
9
| Predicate | Value | Conf. | Basis |
|---|---|---|---|
| ai:documentLikely |
ai-tools heuristic on scan.storage:marac/003/0043.jpg
|
||
| ai:hasText |
Tesseract via ai-tools (0 words, mean conf 95.0)
|
||
| ai:peopleLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0043.jpg
|
| ai:photoLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0043.jpg
|
| ai:photoWithTextLikely | yes | 1% |
ai-tools heuristic on scan.storage:marac/003/0043.jpg
|
| dcterms:type |
people_photo
|
5% |
found 1 face(s)
|
| dcterms:type |
photo
|
5% |
face detection usually implies a photograph; colorfulness 20.2 looks photographic
|
| dcterms:type |
photo_with_text
|
3% |
photo-like image with probable text regions
|
| dcterms:type |
text_present
|
2% |
visual regions suggest some text may be present
|