Triple
T30156144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Save a Prayer |
E766529
|
entity |
| Predicate | isConsideredSignatureSongOf |
P7272
|
FINISHED |
| Object | Duran Duran |
—
|
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: Duran Duran | Statement: [Save a Prayer, isConsideredSignatureSongOf, Duran Duran]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isConsideredSignatureSongOf Context triple: [Save a Prayer, isConsideredSignatureSongOf, Duran Duran]
-
A.
isSignatureSongOf
chosen
Indicates that a particular song is widely recognized as the most iconic or defining song associated with a specific artist or group.
-
B.
hasSignatureSong
Indicates that an artist or performer is especially associated with a particular song that is widely recognized as their defining or most iconic work.
-
C.
isOneOfBestKnownSongsBy
Indicates that the subject song is among the most widely recognized or celebrated songs created by the specified artist or group.
-
D.
isPopularSongOf
Indicates that a song is widely liked, well-known, or frequently enjoyed in relation to a particular entity (such as an artist, album, or context).
-
E.
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.
- 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_69f22479cd088190ab4c6f3fce39d1c5 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6d0d46aec819091edf97324d793ac |
completed | May 3, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe2183481908ae4e85a59c66f69 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 29, 2026, 7:21 p.m.