Triple
T7872053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kathleen Kennedy Townsend |
E182759
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Rory Kennedy |
E182760
|
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: Rory Kennedy | Statement: [Kathleen Kennedy Townsend, sibling, Rory Kennedy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rory Kennedy Context triple: [Kathleen Kennedy Townsend, sibling, Rory Kennedy]
-
A.
Rory Kennedy
chosen
Rory Kennedy is an American documentary filmmaker known for her socially conscious films and as the youngest child of Senator Robert F. Kennedy.
-
B.
Katherine Kelly
Katherine Kelly is a British actress best known for her roles in television dramas such as "Coronation Street" and "Mr Selfridge."
-
C.
Kerry Kennedy
Kerry Kennedy is an American human rights activist, lawyer, and author, and a daughter of Robert F. Kennedy.
-
D.
Gillian Burke
Gillian Burke is a British wildlife biologist, presenter, and filmmaker best known for co-hosting the BBC nature series Springwatch and its related programs.
-
E.
Susan O’Neill
Susan O’Neill was the wife of American film and stage actor Otto Kruger.
- 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_69ca82894d9081908a832bfce71a4714 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb39a5950481908399211c5dfe2569 |
completed | March 31, 2026, 3:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5b6bc7248190adbf4377c52e16a9 |
completed | March 31, 2026, 5:28 a.m. |
Created at: March 30, 2026, 4:56 p.m.