Triple
T37655831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European Book Prize |
E937293
|
entity |
| Predicate | hasFirstEditionLocation |
P202282
|
FINISHED |
| Object | Brussels |
—
|
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: Brussels | Statement: [European Book Prize, hasFirstEditionLocation, Brussels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFirstEditionLocation Context triple: [European Book Prize, hasFirstEditionLocation, Brussels]
-
A.
hasFirstEditionYear
Indicates the year in which the first edition of an item (such as a work, book, or publication) was originally released or published.
-
B.
isFirstEditionOf
Indicates that one entity is the original first published edition of another work or publication.
-
C.
firstEditionFinishLocation
Indicates the location where the first edition of a work was completed or finalized.
-
D.
firstEditionRegion
Indicates the geographic region in which the first edition of a work was originally published.
-
E.
isEarliestCollectedEditionOf
Indicates that one edition of a work is the earliest (in time of collection or acquisition) among all collected editions of that work.
- F. None of above. chosen
Provenance (4 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_69f76ed4fe908190b8061c5c135e0971 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a006be462288190ae18e1567e2ad29f |
completed | May 10, 2026, 11:28 a.m. |
| PD | Predicate disambiguation | batch_6a0069e7a424819098d38458c3823605 |
completed | May 10, 2026, 11:20 a.m. |
| PDg | Predicate description generation | batch_6a006be382308190811a8ee29c262ba1 |
completed | May 10, 2026, 11:28 a.m. |
Created at: May 3, 2026, 4:18 p.m.