Triple
T31820715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Candlewick Press |
E812248
|
entity |
| Predicate | hasNotableIllustrator |
P2761
|
FINISHED |
| Object | Jon Klassen |
—
|
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: Jon Klassen | Statement: [Candlewick Press, hasNotableIllustrator, Jon Klassen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableIllustrator Context triple: [Candlewick Press, hasNotableIllustrator, Jon Klassen]
-
A.
hasNotableIllustrationsOf
Indicates that something contains or features particularly significant or noteworthy illustrations depicting another entity or subject.
-
B.
hasNotableCoverArtist
Indicates that an entity has a cover (e.g., of a book, album, or publication) created by a cover artist who is considered notable.
-
C.
hasNotableCartoonist
Indicates that an entity is associated with a cartoonist who is recognized as notable or distinguished.
-
D.
hasNotableWorkDepiction
Indicates that an entity has a notable work in which it is depicted or represented.
-
E.
hasIllustrationsBy
chosen
Indicates that one entity (such as a work or publication) includes illustrations that were created by another entity (the illustrator).
- 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_69f348e97fa48190aa06286962af6dee |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a00bf5990e08190a8b633e237656564 |
completed | May 10, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_6a00beef4f5881909b00ac89e6af5902 |
completed | May 10, 2026, 5:22 p.m. |
Created at: April 30, 2026, 11:45 p.m.