Triple
T23853297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fox Movietone sound system |
E592229
|
entity |
| Predicate | soundTrackPosition |
P108609
|
FINISHED |
| Object | along the edge of the film |
—
|
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: along the edge of the film | Statement: [Fox Movietone sound system, soundTrackPosition, along the edge of the film]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: soundTrackPosition Context triple: [Fox Movietone sound system, soundTrackPosition, along the edge of the film]
-
A.
discPosition
Indicates the spatial or ordinal placement of a disc relative to a reference point or within a set or structure.
-
B.
positionOnRecord
Indicates the specific place or rank an item occupies within an ordered record or listing.
-
C.
continuityPosition
Indicates the relative ordering or placement of an element within a continuous sequence or flow of related elements.
-
D.
playingPosition
Indicates the specific role or position an individual occupies while participating in a game or sport.
-
E.
soundCarrierOffset
chosen
Indicates the positional or temporal displacement of a sound carrier relative to a defined reference point or baseline.
- 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_69e25d221d908190b9b502ad31e66a3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c98954748190b39e0ac69e5625f9 |
completed | April 29, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:11 p.m.