Triple
T20534638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ryan Bradley |
E504160
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Ryan Bradley |
—
|
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: Ryan Bradley | Statement: [Ryan Bradley, name, Ryan Bradley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ryan Bradley Context triple: [Ryan Bradley, name, Ryan Bradley]
-
A.
Ryan Bradley
chosen
Ryan Bradley is an American figure skater known for competing internationally and winning the 2011 U.S. national championship.
-
B.
Jack Bradley
Jack Bradley is an American local politician who serves as the mayor of Lorain, Ohio.
-
C.
Ryan Brant
Ryan Brant was an American businessman best known as the founding CEO of video game publisher Take-Two Interactive, the company behind major franchises like Grand Theft Auto.
-
D.
Kyle Bradley
Kyle Bradley is an American mixed martial artist known for competing in the UFC’s lightweight division.
-
E.
Bradley Raymond
Bradley Raymond is an American film director best known for his work on animated direct-to-video sequels and spin-offs for Disney, including titles in the Lion King and Tinker Bell franchises.
- 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_69e0b4b476648190bc6019622ae54d3c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a06df04081908fa95c6214f06093 |
completed | April 20, 2026, 9:53 p.m. |
Created at: April 16, 2026, 11:37 a.m.