Triple
T32259763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bianca O'Blivion |
E824118
|
entity |
| Predicate | workOfFictionDirector |
P46167
|
FINISHED |
| Object | David Cronenberg |
—
|
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: David Cronenberg | Statement: [Bianca O'Blivion, workOfFictionDirector, David Cronenberg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workOfFictionDirector Context triple: [Bianca O'Blivion, workOfFictionDirector, David Cronenberg]
-
A.
filmWriterOfWork
Indicates that a person is the writer or screenwriter responsible for creating the script or written content of a particular film.
-
B.
hasDirectorOfWork
Indicates that an entity has a specific person or organization serving as the director responsible for overseeing its work or project.
-
C.
filmDirectorOfAssociatedWork
chosen
Indicates that a person serves as the director of the specified creative work (such as a film or related audiovisual production).
-
D.
genreOfWorkDirected
Indicates that a person has directed a work (such as a film, show, or performance) belonging to a specified genre.
-
E.
fictionalDirectorInSeries
Indicates that a person serves as the director of one or more episodes within a fictional series.
- 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_69f3490db0748190bfef6e50c95d39d3 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bc57134c8190806fe7558f39b44e |
completed | May 3, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69f6b632cf788190a3d0c08cd026b84b |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:41 a.m.