Triple
T19808196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dawn McCarthy |
E475870
|
entity |
| Predicate | collaboratedWith |
P435
|
FINISHED |
| Object | Will Oldham |
—
|
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: Will Oldham | Statement: [Dawn McCarthy, collaboratedWith, Will Oldham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Will Oldham Context triple: [Dawn McCarthy, collaboratedWith, Will Oldham]
-
A.
Will Oldham
chosen
Will Oldham is an American singer-songwriter and actor best known for his influential, lo-fi indie folk music released under the moniker Bonnie "Prince" Billy.
-
B.
Andrew Loog Oldham
Andrew Loog Oldham is a British record producer and former manager best known for shaping the early career and sound of The Rolling Stones in the 1960s.
-
C.
Will Greenwood
Will Greenwood is a former England international rugby union centre who was a key member of the 2003 Rugby World Cup–winning team and later became a prominent television pundit.
-
D.
Roy Greaves
Roy Greaves is a former English footballer best known for his significant contributions to Bolton Wanderers, where he earned a place in the club’s Hall of Fame.
-
E.
Ed Shearmur
Ed Shearmur is a British film composer known for scoring a wide range of Hollywood movies across genres.
- 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_69d8e51bc4208190a1c57d8c5d1b15e4 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65429fec8819091e20908101b50eb |
completed | April 20, 2026, 4:28 p.m. |
Created at: April 10, 2026, 1:49 p.m.