Triple
T10808488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Ann |
E255028
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Joe Bradley |
E260538
|
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: Joe Bradley | Statement: [Princess Ann, associatedWith, Joe Bradley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Bradley Context triple: [Princess Ann, associatedWith, Joe Bradley]
-
A.
Joe Bradley
chosen
Joe Bradley is the charming American journalist who becomes the male lead and romantic interest opposite Audrey Hepburn’s princess in the classic film "Roman Holiday."
-
B.
Bill Bolling
Bill Bolling is an American Republican politician who served as the 39th Lieutenant Governor of Virginia from 2006 to 2014.
-
C.
Stephen Bradley
Stephen Bradley is an American musician and trumpeter best known for performing and touring with the rock band No Doubt.
-
D.
Stephen Bradley
Stephen Bradley is an Irish film and television producer and director known for his work on projects such as the comedy series "Moone Boy."
-
E.
Grant Bardsley
Grant Bardsley is a British voice actor best known for voicing the protagonist Taran in Disney’s animated film "The Black Cauldron."
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733b60c6481909b043565a65f996d |
completed | April 9, 2026, 5:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de8513fe0881909d6833c85aac03a8 |
completed | April 14, 2026, 6:19 p.m. |
Created at: April 8, 2026, 9:18 p.m.