Triple
T22219503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laurie Kenyon |
E549170
|
entity |
| Predicate | hasGuardian |
P28704
|
FINISHED |
| Object | Ted Kenyon |
—
|
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: Ted Kenyon | Statement: [Laurie Kenyon, hasGuardian, Ted Kenyon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ted Kenyon Context triple: [Laurie Kenyon, hasGuardian, Ted Kenyon]
-
A.
Ted Kenyon
chosen
Ted Kenyon is a fictional character known as a close family member in Mary Higgins Clark’s suspense novel "All Around the Town."
-
B.
Curtis Kenyon
Curtis Kenyon was a Hollywood screenwriter active during the early 20th century, known for contributing to several American films including the musical drama "Syncopation."
-
C.
Larry Kenyon
Larry Kenyon is a software engineer best known for his crucial work on performance optimization and system software for the early Apple Macintosh.
-
D.
John Keeler
John Keeler is a fictional U.S. President in the television series "24," succeeding David Palmer in the show's political storyline.
-
E.
Charles Kenyon
Charles Kenyon was an American screenwriter active in early Hollywood, known for adapting literary works and contributing to numerous films during the 1920s and 1930s.
- 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_69e11e403d6481909a94d0aaf157f6ef |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b8edd288190a49f10e009122057 |
completed | April 28, 2026, 9:50 p.m. |
Created at: April 16, 2026, 8:37 p.m.