Triple
T30532480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tsukihi Araragi |
E777041
|
entity |
| Predicate | illustratorOfOriginalWork |
P158166
|
FINISHED |
| Object | VOFAN |
—
|
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: VOFAN | Statement: [Tsukihi Araragi, illustratorOfOriginalWork, VOFAN]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: illustratorOfOriginalWork Context triple: [Tsukihi Araragi, illustratorOfOriginalWork, VOFAN]
-
A.
illustratorOfOriginalCollection
Indicates that an entity served as the illustrator for the original version of a collection of works.
-
B.
illustratorOf
chosen
Indicates that one entity serves as the illustrator or creator of the visual artwork for another entity, such as a book, article, or other work.
-
C.
illustratorOfOriginalLightNovel
Indicates that one entity is the illustrator who created the original artwork for a specific light novel.
-
D.
sameIllustratorAs
Indicates that two entities share the same illustrator, i.e., they were illustrated by the same person or creative source.
-
E.
originalWorkBy
Indicates that one entity is the creator or originator of another entity (such as a work, idea, or product).
- 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_69f2249c11508190ae7e955755ccfb01 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6884deb64819083f346e9ac4824ba |
completed | May 2, 2026, 11:27 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:18 p.m.