Triple
T17701424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reid Ryan |
E441308
|
entity |
| Predicate | childOf |
P120
|
FINISHED |
| Object | Ruth Ryan |
—
|
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: Ruth Ryan | Statement: [Reid Ryan, childOf, Ruth Ryan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ruth Ryan Context triple: [Reid Ryan, childOf, Ruth Ryan]
-
A.
Ruth Ryan
chosen
Ruth Ryan is the longtime wife of Hall of Fame pitcher Nolan Ryan, known for her supportive role throughout his baseball career and their shared involvement in charitable and community activities.
-
B.
Ruth Kearney
Ruth Kearney is an Irish actress known for her television roles, including a starring part in the Netflix series "Flaked."
-
C.
Eileen Welsh Ryan
Eileen Welsh Ryan was a benefactor and namesake of Northwestern University's Welsh-Ryan Arena, recognized for her family's significant contributions to the institution.
-
D.
Dorothy Ryan
Dorothy Ryan was one of the victims killed during the 1987 Hungerford massacre, a mass shooting in Berkshire, England.
-
E.
Ruth McCabe
Ruth McCabe is an Irish actress known for her work in film, television, and theatre, including roles in acclaimed dramas such as "Philomena."
- 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_69d8b9ea20b48190ace88bb46b01e6a9 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4715c3980819094b080a871df1100 |
completed | April 19, 2026, 6:08 a.m. |
Created at: April 10, 2026, 10:04 a.m.