Triple
T19545217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chips Rafferty |
E489026
|
entity |
| Predicate | workedWith |
P398
|
FINISHED |
| Object | Harry Watt |
—
|
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: Harry Watt | Statement: [Chips Rafferty, workedWith, Harry Watt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Watt Context triple: [Chips Rafferty, workedWith, Harry Watt]
-
A.
Stewart Menzies
Stewart Menzies was the head of Britain’s Secret Intelligence Service (MI6) during World War II, overseeing key intelligence operations including those at Bletchley Park.
-
B.
Roeg Sutherland
Roeg Sutherland is a film industry executive and talent agent known for his work in film finance and packaging, and as the son of actor Donald Sutherland.
-
C.
Richie Wise
Richie Wise is a musician best known as a member of the hard rock band Dust.
-
D.
Michael Powell
Michael Powell is an American bookseller and entrepreneur best known as the founder of Powell’s City of Books, one of the world’s largest independent bookstores.
-
E.
Michael Powell
chosen
Michael Powell was a pioneering British film director best known for his visually inventive and psychologically rich collaborations with Emeric Pressburger, such as "The Red Shoes" and "Black Narcissus."
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63875cf40819088db7c7969be1e3d |
completed | April 20, 2026, 2:30 p.m. |
Created at: April 10, 2026, 1:41 p.m.