Triple
T26429054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ryan Fleck |
E664450
|
entity |
| Predicate | directedFilmInFranchise |
P172336
|
FINISHED |
| Object | Marvel Cinematic Universe |
—
|
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: Marvel Cinematic Universe | Statement: [Ryan Fleck, directedFilmInFranchise, Marvel Cinematic Universe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directedFilmInFranchise Context triple: [Ryan Fleck, directedFilmInFranchise, Marvel Cinematic Universe]
-
A.
directedFilmForStudio
Indicates that a person directed a film on behalf of, or under contract with, a particular studio.
-
B.
directedIn
Indicates that one entity served as the director of another entity, such as a person directing a film, episode, or similar work.
-
C.
strategyDirectedBy
Indicates that the development, implementation, or oversight of a strategy is guided or controlled by a specified directing entity.
-
D.
hasFictionalFilmWithinPlay
Indicates that within a theatrical play, there is a fictional film that exists or is depicted as part of the play’s narrative or structure.
-
E.
hasPartInFilmSeries
Indicates that an entity participates in or contributes to one or more installments within a specific film series.
- 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_69ee883ad6a4819088f918e76122d690 |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f6abe15d5c81909ccf4ce37f78bc43 |
completed | May 3, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1c555081908787dbf76147f180 |
completed | May 3, 2026, 1:51 a.m. |
| PDg | Predicate description generation | batch_69f6aaf31a548190b2f792ff4b8c002a |
completed | May 3, 2026, 1:54 a.m. |
Created at: April 26, 2026, 11:47 p.m.