Triple
T22786434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mannix theme |
E563979
|
entity |
| Predicate | inSeriesGenreContext |
P36857
|
FINISHED |
| Object | detective fiction |
—
|
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: detective fiction | Statement: [Mannix theme, inSeriesGenreContext, detective fiction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inSeriesGenreContext Context triple: [Mannix theme, inSeriesGenreContext, detective fiction]
-
A.
curatedSeriesGenre
Indicates that a curated series is associated with, or categorized under, a particular genre.
-
B.
notableGenreSeries
Indicates that a series is notably associated with or recognized for a particular genre.
-
C.
homeSeriesGenre
Indicates that a home media series (such as a TV or video series) belongs to or is categorized under a particular genre.
-
D.
hasGenreInSeries
chosen
Indicates that a particular genre is associated with, or applies to, a work as it appears within a specific series.
-
E.
inSeriesFormat
Indicates that one entity is organized or presented as part of a sequential series format relative to another 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c321f848190a4443aa6bb4e57d7 |
completed | April 29, 2026, 3:34 a.m. |
| PD | Predicate disambiguation | batch_69eed2c32e8c8190b73bb9965ed47d64 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:29 p.m.