Triple
T23032343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matt |
E573496
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Tom Basden |
—
|
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: Tom Basden | Statement: [Matt, portrayedBy, Tom Basden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Basden Context triple: [Matt, portrayedBy, Tom Basden]
-
A.
Tom Basden
chosen
Tom Basden is a British comedian, writer, and actor known for his work in television, radio, and live comedy, often blending sharp wit with offbeat, character-driven humor.
-
B.
Ted Bessell
Ted Bessell was an American television and film actor best known for co-starring as Donald Hollinger on the 1960s sitcom "That Girl."
-
C.
David Bass
David Bass is a person known primarily as the sibling of Richard Bass.
-
D.
Tom Bateman
Tom Bateman is a British actor known for his work in film, television, and theatre, including prominent roles in period dramas and crime mysteries.
-
E.
Edward Bass
Edward Bass is an American businessman and philanthropist best known for financing large-scale environmental and scientific projects, including the Biosphere 2 research facility.
- 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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f184822a90819081907d72c76770b0 |
completed | April 29, 2026, 4:09 a.m. |
Created at: April 17, 2026, 3:53 p.m.