Triple
T30349131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Na-Ga |
E771942
|
entity |
| Predicate | designedCharactersFor |
P57050
|
FINISHED |
| Object | Angel Beats! |
—
|
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: Angel Beats! | Statement: [Na-Ga, designedCharactersFor, Angel Beats!]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designedCharactersFor Context triple: [Na-Ga, designedCharactersFor, Angel Beats!]
-
A.
characterDesigner
chosen
Indicates a relationship where an entity is responsible for designing or creating the visual or conceptual characteristics of a character.
-
B.
coCreatedCharactersWith
Indicates that two or more entities jointly created one or more characters together.
-
C.
franchiseCharacterCreator
Indicates that an entity is the creator or originator of a character that belongs to a particular franchise.
-
D.
usesCharacterDesignFrom
Indicates that one entity employs or incorporates the character design originally created for another entity.
-
E.
developedCharacter
Indicates that one entity created, designed, or otherwise brought into existence the character represented by the other entity.
- 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_69fd49f6dbac81909744373a357b7982 |
completed | May 8, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69fd48ed68f481908374183c66a6b055 |
completed | May 8, 2026, 2:22 a.m. |
Created at: April 29, 2026, 7:56 p.m.