Triple
T20875841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Someday Soon |
E514015
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | Ian Tyson |
—
|
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: Ian Tyson | Statement: [Someday Soon, composer, Ian Tyson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ian Tyson Context triple: [Someday Soon, composer, Ian Tyson]
-
A.
Ian Tyson
chosen
Ian Tyson was a Canadian singer-songwriter and guitarist best known as half of the folk duo Ian and Sylvia and for writing the classic song "Four Strong Winds."
-
B.
Ron Tyson
Ron Tyson is an American soul and R&B singer best known as a longtime tenor and falsetto vocalist with The Temptations.
-
C.
Milan Tyson
Milan Tyson is one of former heavyweight boxing champion Mike Tyson’s daughters, known publicly largely due to her father’s fame.
-
D.
Richard Tyson
Richard Tyson is an American actor best known for playing the menacing villain Cullen Crisp in the action-comedy film "Kindergarten Cop."
-
E.
Jim Barnes
Jim Barnes was an early 20th-century professional golfer known as one of the sport’s pioneering major champions.
- 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_69e0b4f675cc8190b4e745225b62eb66 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c674f68c8190a7b43aeea5b9b976 |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:45 p.m.