Triple
T14487505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Learned |
E359271
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Peter Donat |
E406007
|
NE FINISHED |
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: Peter Donat | Statement: [Michael Learned, spouse, Peter Donat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Donat Context triple: [Michael Learned, spouse, Peter Donat]
-
A.
Peter Donat
chosen
Peter Donat was a Canadian-American actor known for his character roles in film and television, including appearances in "The X-Files" and "The Godfather Part II."
-
B.
David Hayman
David Hayman is a Scottish actor and director known for his intense character roles in film and television, as well as his work in socially conscious drama.
-
C.
Michael Hordern
Michael Hordern was an English actor renowned for his distinguished stage and screen career, often noted for his Shakespearean roles and character work in British film and television.
-
D.
Rupert Davies
Rupert Davies was a British actor best known for his portrayal of Inspector Maigret in the 1960s television series "Maigret."
-
E.
Donald Sinden
Donald Sinden was a distinguished English actor known for his work in film, theatre, and television, particularly from the mid-20th century onward.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d8279740308190af9df93a3af8592e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de924ee0f08190baf68318b41fa64d |
completed | April 14, 2026, 7:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69febfcd67f081909f97bcf38d814a13 |
completed | May 9, 2026, 5:02 a.m. |
Created at: April 10, 2026, 1:20 a.m.