Triple
T18222538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grant Matthews |
E436340
|
entity |
| Predicate | hasAffairWith |
P23617
|
FINISHED |
| Object | Kay Thorndyke |
—
|
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: Kay Thorndyke | Statement: [Grant Matthews, hasAffairWith, Kay Thorndyke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kay Thorndyke Context triple: [Grant Matthews, hasAffairWith, Kay Thorndyke]
-
A.
Kay Thorndyke
chosen
Kay Thorndyke is a powerful and manipulative political influencer in the 1948 film "State of the Union," where she drives much of the story’s intrigue and ambition.
-
B.
Edward Tennant
Edward Tennant was a young British poet and aristocrat of the early 20th century, known for his war poetry and his death in World War I.
-
C.
William Welsh
William Welsh was an early 20th-century American film actor known for his numerous roles in silent-era motion pictures.
-
D.
Julian Harwood
Julian Harwood is an individual notable enough to be recognized as a bearer of the Harwood surname, though specific widely known public details about him are not readily available.
-
E.
Nicholas Gleaves
Nicholas Gleaves is a British actor known for his work in television, film, and theatre, including roles in series such as "Scott & Bailey" and "The Crown."
- 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_69d8b9103a8081908bbb0836fef10efd |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e47c85108190bd9707b40bdfdb38 |
completed | April 19, 2026, 2:19 p.m. |
Created at: April 10, 2026, 10:32 a.m.