Triple
T22587825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vicki Kennedy |
E564847
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Patrick J. Kennedy |
—
|
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: Patrick J. Kennedy | Statement: [Vicki Kennedy, relative, Patrick J. Kennedy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patrick J. Kennedy Context triple: [Vicki Kennedy, relative, Patrick J. Kennedy]
-
A.
Patrick J. Kennedy
chosen
Patrick J. Kennedy is an American former U.S. Representative from Rhode Island and a leading advocate for mental health and addiction policy reform.
-
B.
Patrick J. Kennedy Sr.
Patrick J. Kennedy Sr. was an American politician from Massachusetts and a member of the influential Kennedy family.
-
C.
Patrick Kennedy
Patrick Kennedy is a British actor known for his work in film and television, including prominent roles in period dramas and literary adaptations.
-
D.
Patrick Kennedy
Patrick Kennedy is an American competitive swimmer known for training with the prestigious North Baltimore Aquatic Club.
-
E.
Patrick Kennedy
Patrick Kennedy is an editor known for his work on the publication "Tap."
- 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_69e245836014819091b91ed3074742a3 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1615de7d48190b1ca46c76a1e609c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 2:47 p.m.