Triple
T8935123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | His Last Bow |
E212756
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Sherlock Holmes book |
C6645
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: Sherlock Holmes book Context triple: [His Last Bow, instanceOf, Sherlock Holmes book]
-
A.
Blandings Castle novel
A Blandings Castle novel is a comedic work of fiction by P. G. Wodehouse set in and around the eccentric English country estate of Blandings Castle, typically involving farcical plots, romantic entanglements, and the absent-minded Lord Emsworth.
-
B.
Jeeves and Wooster novel
A Jeeves and Wooster novel is a comedic narrative centered on the misadventures of affable but dim aristocrat Bertie Wooster and his supremely competent valet Jeeves, typically involving romantic entanglements, social mishaps, and Jeeves’s ingenious schemes to restore order.
-
C.
Pinkerton detective
A Pinkerton detective is a private investigator employed by the Pinkerton National Detective Agency, historically known for security work, strikebreaking, and pursuing high-profile criminals in the United States.
-
D.
King's Counsel
A King's Counsel is a senior barrister appointed by the monarch to recognize exceptional advocacy and expertise in the higher courts, typically entrusted with complex and high-profile legal cases.
-
E.
detective fiction series
chosen
A detective fiction series is a collection of interconnected stories or novels that follow one or more investigators as they solve mysteries or crimes, often featuring recurring characters, settings, and thematic elements.
- F. None of above.
Provenance (1 batch)
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_69ca8395c438819087d7cb844ab5990c |
completed | March 30, 2026, 2:07 p.m. |
Created at: March 30, 2026, 6:58 p.m.