Triple
T30343064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Darling in the Franxx |
E771806
|
entity |
| Predicate | chiefDirector |
P63421
|
FINISHED |
| Object | Atsushi Nishigori |
—
|
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: Atsushi Nishigori | Statement: [Darling in the Franxx, chiefDirector, Atsushi Nishigori]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chiefDirector Context triple: [Darling in the Franxx, chiefDirector, Atsushi Nishigori]
-
A.
chief
Indicates that one entity holds the highest-ranking leadership or authoritative position over another entity or within a specified context.
-
B.
chiefStrategist
Indicates that one entity serves as the primary planner and director of strategy for another entity.
-
C.
chiefLieutenantOf
Indicates that one person serves as the primary subordinate or top-ranking assistant to another leader or authority figure.
-
D.
generalDirector
chosen
Indicates that one entity serves as the general director (top executive or chief manager) of another entity, such as an organization or project.
-
E.
chiefSaintOf
Indicates that one entity serves as the principal or primary patron saint associated with another entity (such as a place, group, or institution).
- 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_69f67603526c81908295a1ece8727c66 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:55 p.m.