Triple
T30669600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Adventure of the Second Stain |
E780757
|
entity |
| Predicate | HolmesClient |
P35093
|
FINISHED |
| Object | Trelawney Hope |
—
|
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: Trelawney Hope | Statement: [The Adventure of the Second Stain, HolmesClient, Trelawney Hope]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: HolmesClient Context triple: [The Adventure of the Second Stain, HolmesClient, Trelawney Hope]
-
A.
clientOf
chosen
Indicates that one entity receives services or conducts business from another entity in a client–provider relationship.
-
B.
clientFor
Indicates that one entity acts as a client that uses the services, resources, or interface provided by another entity.
-
C.
modelingClient
Indicates that one entity serves as a client that is being modeled or represented by another entity in a modeling context.
-
D.
managedClient
Indicates that one entity serves as a client that is overseen, administered, or handled operationally by another entity.
-
E.
notableClient
Indicates that one entity serves as a prominent or distinguished client of another entity.
- 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_69f224a7fc208190a07d6d3879b31640 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68b121eac81909e90416207bc1157 |
completed | May 2, 2026, 11:38 p.m. |
| PD | Predicate disambiguation | batch_69f6861170d08190bb98be609d436f84 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:31 p.m.