Triple
T12267516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Okkervil River |
E292383
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Will Sheff |
E973456
|
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: Will Sheff | Statement: [Okkervil River, creator, Will Sheff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Will Sheff Context triple: [Okkervil River, creator, Will Sheff]
-
A.
Will Sheff
chosen
Will Sheff is an American singer-songwriter best known as the frontman and primary songwriter of the indie rock band Okkervil River.
-
B.
Adam Storke
Adam Storke is an American actor best known for his roles in film and television, including his prominent appearance in the miniseries adaptation of Stephen King’s "The Stand."
-
C.
Trevor Upham
Trevor Upham is an American physician and attorney best known as the husband of lawyer and author Cate Edwards, daughter of former U.S. Senator John Edwards.
-
D.
Nic Sheff
Nic Sheff is an American writer and speaker best known for his memoirs about addiction and recovery, including "Tweak," which inspired the film "Beautiful Boy."
-
E.
Grant Shaffer
Grant Shaffer is an American illustrator, storyboard artist, and graphic novelist known for his work in film, advertising, and publishing.
- 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_69d6ab6856488190b5d31178d5015f8e |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91cdd7b3c8190afd237cd9b633d4d |
completed | April 10, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62a93dd948190aeb24c7c50e2f323 |
completed | May 2, 2026, 4:47 p.m. |
Created at: April 8, 2026, 9:52 p.m.