Triple
T9046024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stalker |
E216756
|
entity |
| Predicate | directorFilmographyEntry |
P46167
|
FINISHED |
| Object | Andrei Tarkovsky filmography |
—
|
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: Andrei Tarkovsky filmography | Statement: [Stalker, directorFilmographyEntry, Andrei Tarkovsky filmography]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directorFilmographyEntry Context triple: [Stalker, directorFilmographyEntry, Andrei Tarkovsky filmography]
-
A.
filmDirectorOfAppearance
Indicates that a person served as the director for a specific appearance or segment within a film or audiovisual work.
-
B.
directorSince
Indicates that one entity has held the role of director for another entity starting from a specified point in time.
-
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.
directorPreviousFilm
Indicates that the referenced film is the one a director worked on immediately before the current film.
-
E.
directorsOfFilm
Indicates the person or people who directed a given film.
- 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_69ca83d22d488190adbce5e020e9cd1d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6b4e4b888190a425e29b193b506f |
completed | April 1, 2026, 12:48 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee566b081909e3cdaf551dbd0ec |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:09 p.m.