Triple
T19739233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wakatoshi Ushijima |
E474067
|
entity |
| Predicate | mangaDebut |
P126349
|
FINISHED |
| Object | Haikyuu!! chapter featuring Shiratorizawa introduction |
—
|
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: Haikyuu!! chapter featuring Shiratorizawa introduction | Statement: [Wakatoshi Ushijima, mangaDebut, Haikyuu!! chapter featuring Shiratorizawa introduction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mangaDebut Context triple: [Wakatoshi Ushijima, mangaDebut, Haikyuu!! chapter featuring Shiratorizawa introduction]
-
A.
mangaSerializationStartDate
Indicates the calendar date on which a manga first began its official serialization.
-
B.
mangaka
Indicates that a person is the creator (author and usually illustrator) of a manga work.
-
C.
mangaMagazine
Indicates that a manga work is serialized in or associated with a particular manga magazine.
-
D.
comicsDebut
chosen
Indicates the work, issue, or publication in which an entity first appeared in comics.
-
E.
mangaDemographic
Indicates the target readership demographic that a manga is primarily intended for.
- 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e651607e388190bbb2aaed252820fe |
completed | April 20, 2026, 4:16 p.m. |
| PD | Predicate disambiguation | batch_69e5304a7aac8190ac13f75f0c008e45 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:47 p.m.