Triple
T18382297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Betsy Blair |
E446482
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Kerry Kelly |
—
|
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: Kerry Kelly | Statement: [Betsy Blair, child, Kerry Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kerry Kelly Context triple: [Betsy Blair, child, Kerry Kelly]
-
A.
Kerry Kelly
chosen
Kerry Kelly is the daughter of legendary American dancer, actor, and filmmaker Gene Kelly.
-
B.
Kerry Foster
Kerry Foster is a film producer known for her work on action and genre movies, including the 2010 adaptation of "The Losers."
-
C.
Kelly Kelleher
Kelly Kelleher is the protagonist of Joyce Carol Oates’s novel "Black Water," a young woman whose tragic encounter with a powerful politician mirrors the real-life Chappaquiddick incident.
-
D.
C. Kelly
C. Kelly is a music producer best known for working on the holiday song "Merry Christmas."
-
E.
Andrea Kelly
Andrea Kelly is an American choreographer, dancer, and reality television personality best known for her work in the entertainment industry and for speaking publicly about her marriage to R. Kelly.
- 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_69d8b9f370b88190b1e5081c2c238e7f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e5179c931c8190b1c7c8284f42f7b7 |
completed | April 19, 2026, 5:57 p.m. |
Created at: April 10, 2026, 10:45 a.m.