Triple
T7549374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lover Man |
E178490
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | James Sherman |
E676174
|
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: James Sherman | Statement: [Lover Man, composer, James Sherman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James Sherman Context triple: [Lover Man, composer, James Sherman]
-
A.
James Sherman
chosen
James Sherman is a lyricist best known for writing the words to the jazz standard "Lover Man (Oh, Where Can You Be?)."
-
B.
Sherman Edwards
Sherman Edwards was an American songwriter and composer best known for creating the music and lyrics for the Broadway musical "1776," later adapted into the film of the same name.
-
C.
Howard Sherman
Howard Sherman is an American businessman and film producer best known as the husband of actress Sela Ward.
-
D.
Lowell Sherman
Lowell Sherman was an American actor and film director active in the early 20th century, known for his sophisticated screen presence and for directing early sound films such as "She Done Him Wrong."
-
E.
Jim Douglas
Jim Douglas is an American Republican politician who served as the 80th Governor of Vermont from 2003 to 2011.
- 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_69c69f2cbe08819088f9eb0c03ef529b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f8b35ba481908e1e5bbf329daa33 |
completed | March 27, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c870741e2481909020633203003a68 |
completed | March 29, 2026, 12:21 a.m. |
Created at: March 27, 2026, 3:49 p.m.