Triple
T18335879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dorian Yates |
E439268
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Dorian Yates |
—
|
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: Dorian Yates | Statement: [Dorian Yates, name, Dorian Yates]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dorian Yates Context triple: [Dorian Yates, name, Dorian Yates]
-
A.
Dorian Yates
chosen
Dorian Yates is a legendary English professional bodybuilder renowned for his massively muscular, grainy physique and six consecutive Mr. Olympia titles in the 1990s.
-
B.
Ronnie Coleman
Ronnie Coleman is an American professional bodybuilder widely regarded as one of the greatest in the sport’s history, best known for winning eight Mr. Olympia titles.
-
C.
Frank Zane
Frank Zane is an American bodybuilder renowned for his aesthetic, proportioned physique and three-time Mr. Olympia titles in the late 1970s.
-
D.
Joe Weider
Joe Weider was a pioneering bodybuilding promoter, publisher, and entrepreneur who helped popularize modern fitness culture and created the Mr. Olympia contest.
-
E.
Butch Barbella
Butch Barbella is a musician and composer best known for creating the music for the film "A Bronx Tale."
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ecd759481909703ed2d0d68199f |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:37 a.m.