Triple
T31480572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Adventure of the Stockbroker's Clerk |
E803125
|
entity |
| Predicate | detectivePartner |
P33516
|
FINISHED |
| Object | Dr. John H. Watson |
—
|
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: Dr. John H. Watson | Statement: [The Adventure of the Stockbroker's Clerk, detectivePartner, Dr. John H. Watson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: detectivePartner Context triple: [The Adventure of the Stockbroker's Clerk, detectivePartner, Dr. John H. Watson]
-
A.
detectiveType
Indicates that one entity is classified as a particular type or category of detective in relation to another entity.
-
B.
detectiveMethod
Indicates that one entity uses or is associated with a particular method or technique in the context of detective work or investigation.
-
C.
hasClericalDetective
Indicates that an entity includes or is associated with a detective who is also a member of the clergy.
-
D.
featuresDetectiveDuo
chosen
Indicates that the subject involves or centers around a pair of detectives working together as a team.
-
E.
partnerInCrime
Indicates a relationship where two or more entities collaborate closely in committing or planning wrongful, illicit, or mischievous acts together.
- F. None of above.
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_69f348c9477c8190bc0a21f6d482d2fc |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a5f71b2c8190aade8a83f465be0c |
completed | May 3, 2026, 1:33 a.m. |
| PD | Predicate disambiguation | batch_69f69fe66df08190958558d63ee623d9 |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 9:32 p.m.