Triple
T23251196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ProSieben Maxx |
E581733
|
entity |
| Predicate | animeBlock |
P151544
|
FINISHED |
| Object | daytime anime programming |
—
|
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: daytime anime programming | Statement: [ProSieben Maxx, animeBlock, daytime anime programming]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: animeBlock Context triple: [ProSieben Maxx, animeBlock, daytime anime programming]
-
A.
animeFormat
Indicates the specific production or release format in which an anime is presented (e.g., TV series, movie, OVA, etc.).
-
B.
animatedCharacter
Indicates that an entity is a fictional character depicted through animation rather than live action.
-
C.
animeAdaptationBy
Indicates that one work is an anime adaptation created by a specific person, studio, or organization.
-
D.
animeProducer
Indicates that one entity is the producer responsible for creating, financing, or overseeing the production of an anime work involving the other entity.
-
E.
animeDebut
Indicates the episode, chapter, or installment in which a character, item, or concept first appears in an anime.
- F. None of above. chosen
Provenance (4 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193f7249481909424867e9542d35e |
completed | April 29, 2026, 5:15 a.m. |
| PD | Predicate disambiguation | batch_69effce4d704819092826931d430e8c4 |
completed | April 28, 2026, 12:18 a.m. |
| PDg | Predicate description generation | batch_69f01d8770d081908897c28b04e5faea |
completed | April 28, 2026, 2:37 a.m. |
Created at: April 17, 2026, 4:10 p.m.