Triple
T4880007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yuja Wang |
E109299
|
entity |
| Predicate | studiedUnder |
P7251
|
FINISHED |
| Object | Gary Graffman |
E213668
|
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: Gary Graffman | Statement: [Yuja Wang, studiedUnder, Gary Graffman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gary Graffman Context triple: [Yuja Wang, studiedUnder, Gary Graffman]
-
A.
Gary Graffman
chosen
Gary Graffman is an American classical pianist, renowned pedagogue, and former president of the Curtis Institute of Music who has taught many leading pianists of his generation.
-
B.
Andrew Scheinman
Andrew Scheinman is an American film and television producer and director best known for his work on popular comedies such as "When Harry Met Sally..." and his collaborations with Rob Reiner.
-
C.
James Altman
James Altman is the son of American lawyer and video game executive Robert A. Altman.
-
D.
Douglas Shulman
Douglas Shulman is an American public official who served as the head of the U.S. Internal Revenue Service (IRS) during the late 2000s and early 2010s.
-
E.
Steven Baigelman
Steven Baigelman is an American screenwriter and producer known for his work on biographical and crime dramas in film and television.
- 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_69bd440e9d64819083e82cf33b4d9570 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6dc071d4819083ea9fd0c73c5f49 |
completed | March 20, 2026, 3:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be6803a1c081908972984241276c19 |
completed | March 21, 2026, 9:42 a.m. |
Created at: March 20, 2026, 1:27 p.m.