Triple
T2855594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cinerama film process |
E63191
|
entity |
| Predicate | cameraConfiguration |
P43677
|
FINISHED |
| Object | three 35mm cameras mounted side by side |
—
|
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: three 35mm cameras mounted side by side | Statement: [Cinerama film process, cameraConfiguration, three 35mm cameras mounted side by side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cameraConfiguration Context triple: [Cinerama film process, cameraConfiguration, three 35mm cameras mounted side by side]
-
A.
cameraStyle
Indicates the characteristic visual approach or technique used by a camera in capturing or presenting imagery.
-
B.
rearCameraFeature
Indicates that an entity has a specific characteristic, capability, or attribute related to its rear-facing camera.
-
C.
frontCameraResolution
Indicates the resolution quality or pixel count of a device’s front-facing (selfie) camera.
-
D.
cameraLensType
Indicates the specific type or category of lens used or associated with a camera.
-
E.
hasCamera
Indicates that an entity is equipped with or possesses a camera.
- F. None of above. chosen
Provenance (4 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_69ab4c41e8c08190a9e8f5249cc12610 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf62308081908a65decdd5d6f918 |
completed | March 7, 2026, 8:18 a.m. |
| PD | Predicate disambiguation | batch_69abdd10aef88190b750aae07e7df4dc |
completed | March 7, 2026, 8:08 a.m. |
| PDg | Predicate description generation | batch_69abdee94c2081908e5075e87e70780a |
completed | March 7, 2026, 8:16 a.m. |
Created at: March 6, 2026, 10:02 p.m.