Triple
T9328506
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orchids in the Moonlight |
E224456
|
entity |
| Predicate | lyricist |
P1360
|
FINISHED |
| Object | Gus Kahn |
E555756
|
NE FINISHED |
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: Gus Kahn | Statement: [Orchids in the Moonlight, lyricist, Gus Kahn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gus Kahn Context triple: [Orchids in the Moonlight, lyricist, Gus Kahn]
-
A.
Gus Kahn
chosen
Gus Kahn was a prominent early 20th-century American lyricist known for writing enduring popular standards for Tin Pan Alley and Hollywood films.
-
B.
Jimmy Dorsey
Jimmy Dorsey was an American jazz clarinetist, saxophonist, composer, and big band leader who became one of the most popular bandleaders of the Swing Era.
-
C.
Mitch Miller
Mitch Miller was an American conductor, record producer, and television host best known for his influential work at Columbia Records and his popular sing-along music programs in the 1950s and 1960s.
-
D.
Joe Williams
Joe Williams was a renowned American jazz and blues singer best known for his powerful baritone voice and celebrated recordings with the Count Basie Orchestra.
-
E.
Joe Williams
Joe Williams is a cinematographer best known for his work on the comedy film "Coming 2 America."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8427a0c08190b749831d5ea98f02 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd37ab90ac8190b5c73f08dd091731 |
completed | April 1, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0e3c30ba88190b192621928136b87 |
completed | April 4, 2026, 10:11 a.m. |
Created at: March 30, 2026, 7:39 p.m.