Triple
T23936950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imagine (1971 film sequence at Tittenhurst Park) |
E602663
|
entity |
| Predicate | usesSoundtrack |
P70945
|
FINISHED |
| Object | studio recording of "Imagine" |
—
|
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: studio recording of "Imagine" | Statement: [Imagine (1971 film sequence at Tittenhurst Park), usesSoundtrack, studio recording of "Imagine"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesSoundtrack Context triple: [Imagine (1971 film sequence at Tittenhurst Park), usesSoundtrack, studio recording of "Imagine"]
-
A.
hasSoundtrackCharacteristic
Indicates that a soundtrack possesses a specified quality, feature, or attribute.
-
B.
isSoundtrackOf
Indicates that a piece of music or collection of music serves as the soundtrack for a particular work, such as a film, game, or show.
-
C.
isOnSoundtrack
Indicates that a piece of music is included as part of the official soundtrack for a particular work (such as a film, game, or show).
-
D.
soundtrackFeatures
chosen
Indicates that a particular soundtrack includes or showcases a given piece of music, artist, or audio element as part of its content.
-
E.
sangSoundtrackFor
Indicates that one entity performed or recorded the soundtrack music for a work associated with another entity.
- 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_69e2953cf6e081909b8e25a10a52dddc |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1cfa1336c8190ac307a1b9497ba0b |
completed | April 29, 2026, 9:30 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:05 p.m.