Triple
T30343335
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saekano: How to Raise a Boring Girlfriend |
E771811
|
entity |
| Predicate | lightNovelFirstPublishedIn |
P85637
|
FINISHED |
| Object | Fujimi Fantasia Bunko magazine imprint |
—
|
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: Fujimi Fantasia Bunko magazine imprint | Statement: [Saekano: How to Raise a Boring Girlfriend, lightNovelFirstPublishedIn, Fujimi Fantasia Bunko magazine imprint]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lightNovelFirstPublishedIn Context triple: [Saekano: How to Raise a Boring Girlfriend, lightNovelFirstPublishedIn, Fujimi Fantasia Bunko magazine imprint]
-
A.
lightNovelLabel
Indicates that a work is labeled or classified as a light novel.
-
B.
lightNovelMagazine
chosen
Indicates that a light novel is published in or associated with a particular magazine.
-
C.
lightNovelPublisherCountry
Indicates the country in which the publisher of a given light novel is based.
-
D.
lightNovelDemographic
Indicates the target audience demographic for a given light novel.
-
E.
workOfFictionStartDate
Indicates the date on which a work of fiction was first created, published, released, or otherwise began to exist as a distinct fictional 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_69f2248b9a208190bc3e6804acd5afd6 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6820597308190a7e31f9c6cee3640 |
completed | May 2, 2026, 11 p.m. |
| PD | Predicate disambiguation | batch_69f678ce54b081908c26edfd49e39c60 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 7:55 p.m.