Triple
T37106803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yente (Fiddler on the Roof, Broadway revival) |
E918863
|
entity |
| Predicate | sourceWorkLyricist |
P1360
|
FINISHED |
| Object | Sheldon Harnick |
—
|
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: Sheldon Harnick | Statement: [Yente (Fiddler on the Roof, Broadway revival), sourceWorkLyricist, Sheldon Harnick]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceWorkLyricist Context triple: [Yente (Fiddler on the Roof, Broadway revival), sourceWorkLyricist, Sheldon Harnick]
-
A.
lyricsBy
Indicates that the lyrics of a song or musical work were written or authored by a specified person or entity.
-
B.
writerOfMusicAndLyrics
Indicates that a person is the creator of both the musical composition and the song lyrics for a work.
-
C.
lyricist
chosen
Indicates that one entity is the writer of the words (lyrics) for a musical work associated with another entity.
-
D.
characterInWorkWithLyricsBy
Indicates that a character appears in a creative work whose lyrics were written by a specified lyricist.
-
E.
songWrittenBy
Indicates that a particular song was created or composed by a specific person or group.
- 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_69f76e9b99c8819096164b21ff5bd996 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fbaebc8f2c8190b94f1b4a3ec92e8c |
completed | May 6, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69fbadf1e6008190a71bbd196ba06844 |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:14 p.m.