Triple
T24998458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Persephone Books |
E625641
|
entity |
| Predicate | editionDesign |
P133048
|
FINISHED |
| Object | uniform grey covers |
—
|
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: uniform grey covers | Statement: [Persephone Books, editionDesign, uniform grey covers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: editionDesign Context triple: [Persephone Books, editionDesign, uniform grey covers]
-
A.
edition
Indicates that one entity is a specific version, issue, or release of another (typically a work such as a book, journal, or software).
-
B.
editorialDesignation
Indicates that an entity has been assigned a specific editorial label or status within a publication or editorial workflow.
-
C.
editionPattern
Indicates a recurring structure or template that characterizes how different editions or versions of something are organized or produced.
-
D.
coverDesign
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).
-
E.
designAspect
chosen
Indicates that one entity represents a particular design-related feature, characteristic, or consideration of another entity.
- 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_69e2ff26c50481908bc82e799c9e6587 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f48060597c8190a4414e4e4fcb1fec |
completed | May 1, 2026, 10:28 a.m. |
Created at: April 18, 2026, 6:04 a.m.