Triple
T21643239
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeeves and the Impending Doom |
E534147
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Thomas Gregson |
—
|
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: Thomas Gregson | Statement: [Jeeves and the Impending Doom, featuresCharacter, Thomas Gregson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Gregson Context triple: [Jeeves and the Impending Doom, featuresCharacter, Thomas Gregson]
-
A.
Thomas Gregson
chosen
Thomas Gregson is a fictional New York City police captain and close ally of Sherlock Holmes in the modern-day TV series "Elementary."
-
B.
George Gregan
George Gregan is a former Australian rugby union scrum-half widely regarded as one of the game's greats and the most-capped Wallaby in history.
-
C.
Tom Griffin
Tom Griffin is a film producer best known for his work on the 1986 animated feature "The Transformers: The Movie."
-
D.
Tim Gutterson
Tim Gutterson is a former Army Ranger turned U.S. Marshal and skilled sniper in the television series "Justified," known for his dry wit and loyalty to Raylan Givens.
-
E.
Dennis Ferguson
Dennis Ferguson is a computer networking engineer and entrepreneur best known as one of the founders of Juniper Networks, a major provider of high-performance networking equipment.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c466aec88190ba39c7543dbc8ba2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef53930644819086b0f499e1b8ae63 |
completed | April 27, 2026, 12:16 p.m. |
Created at: April 16, 2026, 6:35 p.m.