Triple
T21164427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pam Ferris |
E521520
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Roger Frost |
—
|
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: Roger Frost | Statement: [Pam Ferris, spouse, Roger Frost]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roger Frost Context triple: [Pam Ferris, spouse, Roger Frost]
-
A.
Ralph Frost
Ralph Frost is an individual notable enough to be recognized as a bearer of the surname Frost.
-
B.
Terry Frost
Terry Frost was a British abstract artist renowned for his vibrant, geometric paintings and prints that became emblematic of post-war modernism in the UK.
-
C.
Warren Frost
chosen
Warren Frost was an American actor best known for his roles in the television series "Twin Peaks" and various film and TV appearances.
-
D.
Fred Rister
Fred Rister was a French DJ and record producer best known for his frequent collaborations with David Guetta on international dance-pop hits.
-
E.
Peter Funt
Peter Funt is an American television personality and producer best known for hosting and continuing his father Allen Funt’s hidden-camera show "Candid Camera."
- 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_69e0b50d1ea481909c07e63c3ead9316 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7270e15bc81908d609198e573040e |
completed | April 21, 2026, 7:28 a.m. |
Created at: April 16, 2026, 2:59 p.m.