Triple
T20176554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Bradley |
E492114
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | John 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: John Bradley | Statement: [James Bradley, father, John Bradley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Bradley Context triple: [James Bradley, father, John Bradley]
-
A.
John Bradley
chosen
John Bradley was a United States Navy corpsman best known as one of the flag raisers on Iwo Jima during World War II, famously depicted in the iconic photograph "Raising the Flag on Iwo Jima."
-
B.
John Bradley
John Bradley is an English actor best known for playing Samwell Tarly in the television series Game of Thrones.
-
C.
Stewart Bradley
Stewart Bradley is an actor known for his role in the film "The Burglar."
-
D.
Andrew Brooke
Andrew Brooke is a British actor known for his roles in television dramas and series, including the 2013 miniseries "The Bible."
-
E.
John Bunn
John Bunn was an American basketball coach and administrator known for his influential roles in college basketball and contributions to the sport’s development.
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e668eb50a48190af7de53680ca2f5d |
completed | April 20, 2026, 5:56 p.m. |
Created at: April 11, 2026, 11:36 p.m.