Triple
T25055205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Elmo's Fire (film) |
E627496
|
entity |
| Predicate | mainThemeSong |
P124012
|
FINISHED |
| Object | St. Elmo's Fire (Man in Motion) |
—
|
NE NERFINISHED |
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: St. Elmo's Fire (Man in Motion) | Statement: [St. Elmo's Fire (film), mainThemeSong, St. Elmo's Fire (Man in Motion)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainThemeSong Context triple: [St. Elmo's Fire (film), mainThemeSong, St. Elmo's Fire (Man in Motion)]
-
A.
hasThemeSong
Indicates that an entity is associated with or characterized by a particular theme song.
-
B.
musicThemeType
Indicates the specific category or type of musical theme associated with a piece, segment, or motif.
-
C.
albumTheme
Indicates that one entity is the central subject, concept, or motif that thematically unifies the other entity, which is an album.
-
D.
filmSongFor
chosen
Indicates that a song was specifically created, selected, or used for a particular film.
-
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_69e2ff2c45f48190afa28369f1df6786 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f454a5472c81909604372f24db8d62 |
completed | May 1, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69f44d77f6e88190a4643ab2cbef567b |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:09 a.m.