Triple
T18968150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Jeremy Thorpe |
E464094
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Caroline Allpass |
—
|
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: Caroline Allpass | Statement: [John Jeremy Thorpe, spouse, Caroline Allpass]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caroline Allpass Context triple: [John Jeremy Thorpe, spouse, Caroline Allpass]
-
A.
Caroline Allpass
chosen
Caroline Allpass was the first wife of British Liberal Party leader Jeremy Thorpe, whose life was cut short in a car accident in the early 1970s.
-
B.
June Carryl
June Carryl is an American actress and playwright known for her work in television, film, and theater, including a prominent role in the Marvel television series "Helstrom."
-
C.
Mary Crosby
Mary Crosby is an American actress best known for her role as Kristin Shepard on the television series "Dallas."
-
D.
Audra Lindley
Audra Lindley was an American actress best known for her role as the quirky landlady Helen Roper on the television sitcom "Three's Company" and its spin-off "The Ropers."
-
E.
Laura Allen
Laura Allen is an American actress best known for her role as Lily Moore on the science fiction television series "The 4400."
- 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6172888819090a8b3cb1db20496 |
completed | April 20, 2026, 7:30 a.m. |
Created at: April 10, 2026, noon