Triple
T35034773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | What We See When We Read |
E1010878
|
entity |
| Predicate | authorOfCoverDesign |
P145323
|
FINISHED |
| Object | Peter Mendelsund |
—
|
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: Peter Mendelsund | Statement: [What We See When We Read, authorOfCoverDesign, Peter Mendelsund]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorOfCoverDesign Context triple: [What We See When We Read, authorOfCoverDesign, Peter Mendelsund]
-
A.
hasAuthorNameOnCover
Indicates that the name of the author is printed or displayed on the cover of the work.
-
B.
coverDesign
chosen
Indicates that one entity is responsible for creating or specifying the visual design of another entity’s cover (such as a book, album, or publication).
-
C.
authorRealNameNotOnOriginalCover
Indicates that the work’s original cover does not display the author’s real name.
-
D.
coverArtistOf
Indicates that one entity is the artist who created the cover artwork for another entity, such as a book, album, or publication.
-
E.
coverArtistFirstEdition
Indicates that an entity served as the cover artist specifically for the first edition of another work.
- 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_69f76dcea02c81908542a223f6d5059f |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fdec5ffe088190ac5505f26c6cff18 |
completed | May 8, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69fdeae15f1c81908fc63fbc1b028d2e |
completed | May 8, 2026, 1:53 p.m. |
Created at: May 3, 2026, 4:01 p.m.