Triple
T7060116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Stross |
E164193
|
entity |
| Predicate | influencedBy |
P9
|
FINISHED |
| Object | Len Deighton |
E350242
|
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: Len Deighton | Statement: [Charles Stross, influencedBy, Len Deighton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Len Deighton Context triple: [Charles Stross, influencedBy, Len Deighton]
-
A.
Len Deighton
chosen
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.
-
B.
Frederick Forsyth
Frederick Forsyth is a British thriller writer renowned for his meticulously researched, politically charged novels such as "The Day of the Jackal."
-
C.
Jeffrey Archer
Jeffrey Archer is a British author and former politician best known for his bestselling novels and thrillers.
-
D.
John le Carré
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.
-
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 (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_69c688796c148190adb2f1596f595f22 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e458ad9c81908c3f492b317ce291 |
completed | March 27, 2026, 8:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c788af20cc819084542035410aafbd |
completed | March 28, 2026, 7:52 a.m. |
Created at: March 27, 2026, 2:38 p.m.