Triple
T30343767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horimiya |
E771820
|
entity |
| Predicate | characterDesignBy |
P57050
|
FINISHED |
| Object | Haruko Iizuka |
—
|
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: Haruko Iizuka | Statement: [Horimiya, characterDesignBy, Haruko Iizuka]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterDesignBy Context triple: [Horimiya, characterDesignBy, Haruko Iizuka]
-
A.
characterDesigner
chosen
Indicates a relationship where an entity is responsible for designing or creating the visual or conceptual characteristics of a character.
-
B.
usesCharacterDesignFrom
Indicates that one entity employs or incorporates the character design originally created for another entity.
-
C.
characterCreator
Indicates that one entity is the creator or originator of a character associated with another entity.
-
D.
characterArtForm
Indicates a relationship where a character is associated with, depicted in, or expressed through a particular artistic form or medium.
-
E.
coloristCharacterDesign
Indicates that the colorist is responsible for determining or applying the color scheme for a character’s design.
- 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_69fde49a084081909d99b1e0258169d5 |
completed | May 8, 2026, 1:26 p.m. |
| PD | Predicate disambiguation | batch_69fde1d04bd881909a46ecbbf18dfe59 |
completed | May 8, 2026, 1:14 p.m. |
Created at: April 29, 2026, 7:55 p.m.