Triple
T24786014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Grant |
E620117
|
entity |
| Predicate | publisherOfPrimarySeries |
P92830
|
FINISHED |
| Object | Gollancz |
—
|
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: Gollancz | Statement: [Peter Grant, publisherOfPrimarySeries, Gollancz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publisherOfPrimarySeries Context triple: [Peter Grant, publisherOfPrimarySeries, Gollancz]
-
A.
publisherOfSeries
chosen
Indicates that an entity serves as the publishing organization responsible for producing or distributing a particular series.
-
B.
publisherOfFranchise
Indicates that an entity serves as the publishing company responsible for releasing or distributing a particular franchise.
-
C.
publisherInUniverse
Indicates that a publisher operates, exists, or is recognized within a particular fictional or conceptual universe.
-
D.
firstPublisher
Indicates that an entity is the original or earliest publisher of another entity (such as a work, edition, or resource).
-
E.
publisherParentCompany
Indicates that one company serves as the parent (owning or controlling) company of a given publisher.
- 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_69e2fabdbe8c8190adbb9434b8636cad |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f453035f508190be83a3d521723acf |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f44d6ef33081908f5d36ba1ae5f473 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 4:45 a.m.