Triple
T2461474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frances Ha |
E54542
|
entity |
| Predicate | screenAspect |
P1991
|
FINISHED |
| Object | black-and-white digital cinematography |
—
|
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: black-and-white digital cinematography | Statement: [Frances Ha, screenAspect, black-and-white digital cinematography]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenAspect Context triple: [Frances Ha, screenAspect, black-and-white digital cinematography]
-
A.
aspectRatio
chosen
Indicates the proportional relationship between an entity’s width and its height.
-
B.
mediaAspect
Indicates the specific aspect ratio or dimensional proportion of a media item in relation to its width and height.
-
C.
displayResolution
Indicates the relationship specifying the width and height dimensions at which visual content is rendered or shown on a display.
-
D.
televisionAspect
Indicates the aspect ratio or format characteristics of a television display in relation to its width and height proportions.
-
E.
typicalResolution
Indicates the usual or standard level of detail or clarity at which something (such as an image, display, or representation) is normally rendered or presented.
- 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_69ab49dee84c819096b50a0049c347ac |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd49c5aa081909ab4f726a458b77f |
completed | March 7, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69abd0b199488190aa381b36593ae1ac |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:44 p.m.