Triple
T6875170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stephanie "Stiffy" Byng |
E158653
|
entity |
| Predicate | typicalInteractionWithJeeves |
P30538
|
FINISHED |
| Object | benefits from Jeeves’s problem-solving |
—
|
LITERAL 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: benefits from Jeeves’s problem-solving | Statement: [Stephanie "Stiffy" Byng, typicalInteractionWithJeeves, benefits from Jeeves’s problem-solving]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalInteractionWithJeeves Context triple: [Stephanie "Stiffy" Byng, typicalInteractionWithJeeves, benefits from Jeeves’s problem-solving]
-
A.
toolUse
Indicates that an entity uses or employs another entity as a tool to perform an action or achieve a goal.
-
B.
assistant
chosen
Indicates that one entity provides help, support, or services to another entity.
-
C.
coPilotWith
Indicates that two entities jointly serve as pilots or share piloting responsibilities for the same vehicle or mission.
-
D.
toolUseExamples
Indicates that one entity provides example instances or demonstrations of how a particular tool is or can be used by another entity.
-
E.
commonsSpeaker
Indicates that a person serves as the Speaker (presiding officer) of the House of Commons.
- 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_69c68832af1481908ce356e133ebaebe |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d8c9e7b481909079b0f1fb1bc217 |
completed | March 27, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b363dc8190a7225b540ab2bc40 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:22 p.m.