Triple
T23772608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eyes on Me |
E587571
|
entity |
| Predicate | isEnglishLanguageSongBy |
P11404
|
FINISHED |
| Object | Celine Dion |
—
|
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: Celine Dion | Statement: [Eyes on Me, isEnglishLanguageSongBy, Celine Dion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isEnglishLanguageSongBy Context triple: [Eyes on Me, isEnglishLanguageSongBy, Celine Dion]
-
A.
lyricsLanguage
chosen
Indicates the language in which the lyrics of a song or musical work are written or performed.
-
B.
isSongIn
Indicates that a particular song is contained within or belongs to a specified collection, such as an album, playlist, or soundtrack.
-
C.
isPopularSongFrom
Indicates that a song is widely liked, well-known, or frequently played and originates from a particular source, such as an artist, album, or media work.
-
D.
hasArtistLanguage
Indicates that an artist is associated with, or primarily uses, a particular language in their work or identity.
-
E.
isPopularSongFor
Indicates that a song is widely liked, well-known, or frequently chosen by a particular audience, group, or context.
- 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_69e2490d245881909028226a1393d624 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1c467e6588190aab28bc5a8e43e80 |
completed | April 29, 2026, 8:42 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:15 p.m.