Triple
T23778662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Claude Pickens |
E587746
|
entity |
| Predicate | imageCollectionType |
P102816
|
FINISHED |
| Object | glass lantern slides |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: glass lantern slides | Statement: [Claude Pickens, imageCollectionType, glass lantern slides]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: imageCollectionType Context triple: [Claude Pickens, imageCollectionType, glass lantern slides]
-
A.
typeOfStills
Indicates that one entity is a specific kind or category of stills (e.g., a particular type or style within the broader class of still images or still photography).
-
B.
hasImageryType
Indicates that one entity is associated with a specific kind or category of imagery (such as visual style, medium, or representation type) used to depict or describe it.
-
C.
principalImageType
Indicates the primary or most representative type of image associated with an entity.
-
D.
imageOf
Indicates that one entity is a visual representation or depiction of another entity.
-
E.
collectionFeature
chosen
Indicates that a collection possesses or is characterized by a particular feature or attribute.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e2490d245881909028226a1393d624 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1c629f0c08190baccce71ebc72650 |
completed | April 29, 2026, 8:49 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:16 p.m.