Triple
T20121583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeffrey Caine |
E490620
|
entity |
| Predicate | basedOnWorkBy |
P2806
|
FINISHED |
| Object | John le Carré |
—
|
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: John le Carré | Statement: [Jeffrey Caine, basedOnWorkBy, John le Carré]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John le Carré Context triple: [Jeffrey Caine, basedOnWorkBy, John le Carré]
-
A.
John le Carré
chosen
John le Carré was a renowned British novelist best known for his sophisticated espionage thrillers that explored the moral ambiguities of Cold War intelligence work.
-
B.
Len Deighton
Len Deighton is a British author and historian best known for his spy novels, including "The IPCRESS File," and his influential works on military history.
-
C.
Frederick Forsyth
Frederick Forsyth is a British thriller writer renowned for his meticulously researched, politically charged novels such as "The Day of the Jackal."
-
D.
Ian Fleming
Ian Fleming was a British author and journalist best known as the creator of the James Bond spy novels.
-
E.
Philip Kerr
Philip Kerr was a British author best known for his Bernie Gunther series of historical crime novels set in Nazi and post-war Germany.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6673e79dc81908fbd387c067fce79 |
completed | April 20, 2026, 5:49 p.m. |
Created at: April 11, 2026, 11:30 p.m.