Triple
T21780325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Sinatra Sings for Only the Lonely |
E537692
|
entity |
| Predicate | coverArtType |
P127526
|
FINISHED |
| Object | caricature of Frank Sinatra as a sad clown |
—
|
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: caricature of Frank Sinatra as a sad clown | Statement: [Frank Sinatra Sings for Only the Lonely, coverArtType, caricature of Frank Sinatra as a sad clown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coverArtType Context triple: [Frank Sinatra Sings for Only the Lonely, coverArtType, caricature of Frank Sinatra as a sad clown]
-
A.
coverArtForm
Indicates the artistic medium or format used for the cover artwork associated with an item.
-
B.
coverArtText
Indicates that the text element is part of, or associated with, the cover art of a work.
-
C.
coverArtDescription
chosen
Indicates a textual description that explains or characterizes the visual content of an item's cover art.
-
D.
coverArtDepicts
Indicates that the subject cover art visually represents, portrays, or includes the object within its imagery.
-
E.
coverArtFeaturesColor
Indicates that the cover art includes or prominently displays a specific color as part of its visual design.
- 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_69e0c470759c819094a215757113562b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0462cae6481908d3e7f71683d8921 |
completed | April 28, 2026, 5:31 a.m. |
| PD | Predicate disambiguation | batch_69e6be6299988190a34c98fa76d94700 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:52 p.m.