Triple
T19263873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bessette |
E481719
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Lauren Bessette |
—
|
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: Lauren Bessette | Statement: [Bessette, hasNotableBearer, Lauren Bessette]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lauren Bessette Context triple: [Bessette, hasNotableBearer, Lauren Bessette]
-
A.
Lauren Bessette
chosen
Lauren Bessette was an American investment banker and the sister of Carolyn Bessette-Kennedy, who died alongside her in the 1999 plane crash with John F. Kennedy Jr.
-
B.
Elizabeth Daley
Elizabeth Daley is one of the daughters of the late Chicago First Lady Maggie Daley and former Chicago Mayor Richard M. Daley.
-
C.
Stephanie Beacham
Stephanie Beacham is a British actress known for her work in television dramas and soap operas, including prominent roles in series like Dynasty and The Colbys.
-
D.
Amy Joanne Robach
Amy Joanne Robach is an American television journalist and news anchor best known for her work on ABC News programs such as Good Morning America and 20/20.
-
E.
Lisa Marie Stetler
Lisa Marie Stetler is a film producer known for her work on the animated feature "Ferdinand."
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fb8bce6881908395836960762672 |
completed | April 20, 2026, 10:10 a.m. |
Created at: April 10, 2026, 1:28 p.m.