Triple
T31922990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Babyface portrait |
E815023
|
entity |
| Predicate | coverArtFor |
P159880
|
FINISHED |
| Object | Return of the Tender Lover |
—
|
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: Return of the Tender Lover | Statement: [Babyface portrait, coverArtFor, Return of the Tender Lover]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coverArtFor Context triple: [Babyface portrait, coverArtFor, Return of the Tender Lover]
-
A.
coverArtText
Indicates that the text element is part of, or associated with, the cover art of a work.
-
B.
coverArtForm
Indicates the artistic medium or format used for the cover artwork associated with an item.
-
C.
coverArtDepicts
Indicates that the subject cover art visually represents, portrays, or includes the object within its imagery.
-
D.
isCoverArtFor
chosen
Indicates that one item serves as the cover artwork or visual representation for another item, such as a publication, recording, or product.
-
E.
coverArtUpdate
Indicates an action where the visual cover artwork associated with an item is changed or replaced with a new version.
- 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_69f348f1df848190851bbfb988da3414 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7b2f3a104819098ddd8909eaf596c |
completed | May 3, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 1, 2026, 12:03 a.m.