Triple
T12107221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MGM Camera 65 |
E288332
|
entity |
| Predicate | captureFormat |
P13218
|
FINISHED |
| Object | 65 mm negative |
—
|
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: 65 mm negative | Statement: [MGM Camera 65, captureFormat, 65 mm negative]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: captureFormat Context triple: [MGM Camera 65, captureFormat, 65 mm negative]
-
A.
sensorFormat
Indicates the data encoding or representation standard used by a sensor to output its measurements.
-
B.
captureType
Indicates the manner or method by which something is captured, recorded, or acquired in the context of the relationship.
-
C.
typicalPictureFormat
chosen
Indicates the standard or most commonly used picture format associated with an entity (such as a device, medium, or context).
-
D.
projectionFormat
Indicates the specific technical format or method used to project visual content (such as film or digital media) onto a display surface.
-
E.
detectorFormat
Indicates the specific data or signal representation used by a detector to encode or output its measurements.
- 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_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9164ada5081908676bd9e5947268a |
completed | April 10, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69d9150497408190921334d21503375a |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:49 p.m.