Triple
T16655704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George R. Kelly |
E404721
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Kathryn Kelly |
E119199
|
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: Kathryn Kelly | Statement: [George R. Kelly, spouse, Kathryn Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kathryn Kelly Context triple: [George R. Kelly, spouse, Kathryn Kelly]
-
A.
Kathryn Kelly
chosen
Kathryn Kelly was an American criminal best known for partnering with her husband, gangster George "Machine Gun" Kelly, in high-profile kidnappings during the early 1930s.
-
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.
Kathy Walsh
Kathy Walsh is a notable individual recognized for achievements significant enough to be distinguished among others sharing the Walsh surname.
-
D.
Kathleen Kelly
Kathleen Kelly is the daughter of Kansas Governor Laura Kelly.
-
E.
Kathleen Kelly
Kathleen Kelly is the charming independent bookstore owner portrayed by Meg Ryan in the romantic comedy film "You've Got Mail."
- 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_69d8838b5fbc81908c6575c132b82e80 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37bfa45d8819081bf8579a7160389 |
completed | April 18, 2026, 12:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c79657ec8190b1b3500b7a99df0a |
completed | May 10, 2026, 5:59 p.m. |
Created at: April 10, 2026, 5:18 a.m.