Triple
T36424265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baby's on the Way |
E897244
|
entity |
| Predicate | isRecordedTrackOn |
P3284
|
FINISHED |
| Object | I'll Stay Me |
—
|
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: I'll Stay Me | Statement: [Baby's on the Way, isRecordedTrackOn, I'll Stay Me]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isRecordedTrackOn Context triple: [Baby's on the Way, isRecordedTrackOn, I'll Stay Me]
-
A.
isRecordedMusic
Indicates that something is music that has been captured and stored in a recorded form, rather than being performed live in the moment.
-
B.
isRecordedMusicFor
Indicates that one entity is music that has been recorded specifically to accompany, represent, or be used with another entity (such as a work, event, or medium).
-
C.
hasRecordingWith
Indicates that one entity is associated with or includes a particular recording as part of its content or representation.
-
D.
hasTrack
chosen
Indicates that one entity possesses, includes, or is associated with a specific track (such as a path, course, or recorded item).
-
E.
containsReRecordedSong
Indicates that one entity (typically an album, release, or collection) includes a song that has been recorded again in a new version compared to its original recording.
- 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_69f76e559b10819099d6655a6e14587c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bcccd7988190aa5c931ff347d33c |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:10 p.m.