Triple
T22663463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dum Maro Dum |
E559720
|
entity |
| Predicate | lyricistFullName |
P1360
|
FINISHED |
| Object | Anand Bakshi |
—
|
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: Anand Bakshi | Statement: [Dum Maro Dum, lyricistFullName, Anand Bakshi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lyricistFullName Context triple: [Dum Maro Dum, lyricistFullName, Anand Bakshi]
-
A.
lyricist
chosen
Indicates that one entity is the writer of the words (lyrics) for a musical work associated with another entity.
-
B.
lyricistOfSourcePoem
Indicates that one entity is the writer of the original poem on which another work (such as a song or adaptation) is based.
-
C.
writerOfMusicAndLyrics
Indicates that a person is the creator of both the musical composition and the song lyrics for a work.
-
D.
notableLyricist
Indicates that the subject is a lyricist who is particularly distinguished or well-known for their work.
-
E.
hasComposerLyricistTeam
Indicates a relationship where a musical work is associated with a specific team that jointly fulfills the roles of composer and lyricist.
- 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_69e2454a158c819093b8e35f5045efb6 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f176617ed8819095a58a2c9f1e3918 |
completed | April 29, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69ee62a6245881909506ff502da14137 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:08 p.m.