Triple
T12483468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Subway Portraits |
E298371
|
entity |
| Predicate | cameraUse |
P58520
|
FINISHED |
| Object | concealed camera under clothing |
—
|
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: concealed camera under clothing | Statement: [Subway Portraits, cameraUse, concealed camera under clothing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cameraUse Context triple: [Subway Portraits, cameraUse, concealed camera under clothing]
-
A.
usesCameraType
chosen
Indicates that one entity employs or operates a specific type or category of camera.
-
B.
usesCameraApp
Indicates that an entity operates or interacts with a camera application to capture photos, record videos, or manage camera-related functions.
-
C.
cameraConfiguration
Indicates the specific setup or arrangement of a camera’s parameters or components in a given context.
-
D.
frontCameraFeature
Indicates that an entity has a specified feature, capability, or characteristic associated with its front-facing camera.
-
E.
cameraStyle
Indicates the characteristic visual approach or technique used by a camera in capturing or presenting imagery.
- 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_69d6ada377208190a36011199a4d8558 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94e8a706c8190873623eab7db607d |
completed | April 10, 2026, 7:24 p.m. |
| PD | Predicate disambiguation | batch_69d94d41f3cc8190a3331fb9a895306f |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:56 p.m.