Triple
T30046679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Balu Mahendra |
E763472
|
entity |
| Predicate | cinematographed |
P1953
|
FINISHED |
| Object | Kokila |
—
|
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: Kokila | Statement: [Balu Mahendra, cinematographed, Kokila]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cinematographed Context triple: [Balu Mahendra, cinematographed, Kokila]
-
A.
cinematographyBy
chosen
Indicates that the cinematographic work (such as the camera work or visual style of a film or video) is created or supervised by a specified person or entity.
-
B.
cinematicForm
Indicates that something is expressed, structured, or realized through the techniques, conventions, or medium of cinema or film.
-
C.
cinematographyIncludes
Indicates that a cinematographic work or process contains or makes use of specific visual techniques, elements, or components as part of its overall execution.
-
D.
recordedForFilm
Indicates that an audio or performance was captured specifically for use in a film production.
-
E.
cinematicContext
Indicates the relationship in which something is situated within, shaped by, or relevant to the circumstances, style, or conventions of cinema or 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_69f22470a89c8190be7273297c0e0d19 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67a12ee4881908418a2814ac05db8 |
completed | May 2, 2026, 10:26 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 6:54 p.m.