Triple
T19952529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herbie Mann |
E479595
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Herbie Mann |
—
|
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: Herbie Mann | Statement: [Herbie Mann, name, Herbie Mann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herbie Mann Context triple: [Herbie Mann, name, Herbie Mann]
-
A.
Herbie Mann
chosen
Herbie Mann was an influential American jazz flutist and bandleader known for pioneering the fusion of jazz with world music styles such as Latin, Brazilian, and Middle Eastern music.
-
B.
Alan Balsam
Alan Balsam is a film editor best known for his work on the comedy sequel "Police Academy 4: Citizens on Patrol."
-
C.
Earl Klugh
Earl Klugh is an American acoustic guitarist and composer known for his smooth jazz style and melodic, crossover-friendly instrumental recordings.
-
D.
Bobby Caldwell
Bobby Caldwell was an American singer, songwriter, and multi-instrumentalist best known for his smooth blend of R&B, soul, and jazz, particularly the classic hit "What You Won't Do for Love."
-
E.
Charlie Weber
Charlie Weber is an American actor best known for playing Frank Delfino on the television drama series "How to Get Away with Murder."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e522a17c819095165d4d24939fd8 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65a6c87388190a1bada3117acaf7b |
completed | April 20, 2026, 4:55 p.m. |
Created at: April 10, 2026, 1:54 p.m.