Triple
T8243644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kinuko Y. Craft |
E192795
|
entity |
| Predicate | hasCreatedCoverArtFor |
P56626
|
FINISHED |
| Object | Patricia A. McKillip books |
—
|
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: Patricia A. McKillip books | Statement: [Kinuko Y. Craft, hasCreatedCoverArtFor, Patricia A. McKillip books]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCreatedCoverArtFor Context triple: [Kinuko Y. Craft, hasCreatedCoverArtFor, Patricia A. McKillip books]
-
A.
hasCoverArtFeaturing
Indicates that one entity’s cover art visually features or depicts another entity.
-
B.
hasCoverArtSource
Indicates that an entity’s cover art is derived from, or visually based on, another specified source entity.
-
C.
hasCoverArtTheme
Indicates that an item’s cover art visually represents or is characterized by a particular theme or motif.
-
D.
hasCoverArtVariant
Indicates that an item has an alternative version of its cover artwork distinct from the primary cover.
-
E.
hasNotableCoverArtist
chosen
Indicates that an entity has a cover (e.g., of a book, album, or publication) created by a cover artist who is considered notable.
- 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_69ca82de7b8c81908d8106f8a53cff9b |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb786f65708190a92ec282b280c813 |
completed | March 31, 2026, 7:31 a.m. |
| PD | Predicate disambiguation | batch_69cb36b437e881909958591357e83b9d |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:47 p.m.