Triple
T33030795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curtis Publishing Company Building |
E845157
|
entity |
| Predicate | artworkFabricator |
P21901
|
FINISHED |
| Object | Louis Comfort Tiffany |
—
|
NE NERFINISHED |
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: Louis Comfort Tiffany | Statement: [Curtis Publishing Company Building, artworkFabricator, Louis Comfort Tiffany]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: artworkFabricator Context triple: [Curtis Publishing Company Building, artworkFabricator, Louis Comfort Tiffany]
-
A.
artworkFunction
Indicates the purpose or role that an artwork is intended to serve or perform.
-
B.
artwork
Indicates that one entity is an artwork created, presented, or associated with another entity (such as an artist, collection, or institution).
-
C.
artworkType
Indicates the specific category or kind of artwork that characterizes the relationship between the subject and the artwork.
-
D.
wallpaperDesigner
Indicates that one entity is the designer or creator of the wallpaper associated with another entity.
-
E.
artworkBy
chosen
Indicates that one entity is the creator or artist responsible for producing the other entity as an artwork.
- 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_69f34950749c8190ae05cd27adb16d58 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:24 a.m.