Triple
T12295837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ultra Panavision 70 |
E293083
|
entity |
| Predicate | projectionPrintWidth |
P103320
|
FINISHED |
| Object | 70 mm |
—
|
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: 70 mm | Statement: [Ultra Panavision 70, projectionPrintWidth, 70 mm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: projectionPrintWidth Context triple: [Ultra Panavision 70, projectionPrintWidth, 70 mm]
-
A.
printWidth
chosen
Indicates the width setting or constraint used when formatting or printing content, such as text or code.
-
B.
projectionPrintType
Indicates the method or format by which a projection is printed or rendered (e.g., type or style of the projection output).
-
C.
projectionPrintsBlownUpFrom
Indicates that a projection print was created by enlarging or blowing up an image from another source material.
-
D.
printLayout
Indicates that one entity arranges and formats content for physical or virtual printing according to a specified layout.
-
E.
projectionFormat
Indicates the specific technical format or method used to project visual content (such as film or digital media) onto a display surface.
- 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_69d6ab690ad081908c0ed3870ec82d53 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f621570819091ee1db2609233ea |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ec02c008190a56aae60a3d9eff6 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:52 p.m.