Triple
T17812551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deborah Watling |
E444747
|
entity |
| Predicate | workedWith |
P398
|
FINISHED |
| Object | Frazer Hines |
—
|
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: Frazer Hines | Statement: [Deborah Watling, workedWith, Frazer Hines]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frazer Hines Context triple: [Deborah Watling, workedWith, Frazer Hines]
-
A.
Frazer Hines
chosen
Frazer Hines is a British actor best known for his long-running role as companion Jamie McCrimmon in the classic science fiction television series Doctor Who.
-
B.
Norman Fell
Norman Fell was an American character actor best known for his role as landlord Mr. Roper on the television sitcom "Three's Company."
-
C.
Bernard Lee
Bernard Lee was a British actor best known for playing M, James Bond’s boss, in the early James Bond films.
-
D.
John Thaw
John Thaw was a renowned English actor best known for his iconic role as Inspector Morse in the long-running British television series of the same name.
-
E.
John Nettles
John Nettles is a British actor best known for starring as Detective Chief Inspector Tom Barnaby in the long-running television crime drama "Midsomer Murders."
- 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4887c63608190b29a407cabff0bc5 |
completed | April 19, 2026, 7:47 a.m. |
Created at: April 10, 2026, 10:14 a.m.