Triple
T28102564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | As I Was Moving Ahead Occasionally I Saw Brief Glimpses of Beauty |
E710273
|
entity |
| Predicate | footageSpan |
P10692
|
FINISHED |
| Object | several decades |
—
|
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: several decades | Statement: [As I Was Moving Ahead Occasionally I Saw Brief Glimpses of Beauty, footageSpan, several decades]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: footageSpan Context triple: [As I Was Moving Ahead Occasionally I Saw Brief Glimpses of Beauty, footageSpan, several decades]
-
A.
storyTimeSpanInFilm
chosen
Indicates the duration of time that the story or narrative covers within the film.
-
B.
supportsVideoLengthRange
Indicates that an entity is compatible with or allows videos whose durations fall within a specified minimum-to-maximum time range.
-
C.
filmLength
Indicates the duration or running time of a film, typically measured in units such as minutes.
-
D.
maximumVideoLength
Indicates the greatest allowable or supported duration for a video in this context.
-
E.
frameDuration
Indicates the length of time that a single frame in a sequence (such as video or animation) is displayed before advancing to the next frame.
- 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_69ef9b71fdb081908b4a61cd7ff147c1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6409275e081909c3f102b56d1f132 |
completed | May 2, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 9:06 p.m.