Triple
T20453624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boiling Point |
E501717
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Jason Flemyng |
—
|
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: Jason Flemyng | Statement: [Boiling Point, starring, Jason Flemyng]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jason Flemyng Context triple: [Boiling Point, starring, Jason Flemyng]
-
A.
Jason Flemyng
chosen
Jason Flemyng is an English actor known for his character roles in films such as "Lock, Stock and Two Smoking Barrels," "Snatch," and various Hollywood and British productions.
-
B.
Ian Lansbury
Ian Lansbury is a television producer and member of the Lansbury family, the grandson of acclaimed actress Angela Lansbury.
-
C.
Colin Lambert
Colin Lambert is a character from the British sitcom "Rev." who appears as a friend within the show's clergy-centered social circle.
-
D.
Jonathan Rees
Jonathan Rees is a computer scientist and software engineer known for his contributions to the Scheme programming language and programming language theory.
-
E.
Jonathan Brackley
Jonathan Brackley is a British television writer and producer best known for co-creating and writing the sci-fi drama series "Humans."
- 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_69e0b4ac0a1c81908845d0f8a56abce8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e68d04ca4081909b428c31d16fca10 |
completed | April 20, 2026, 8:31 p.m. |
Created at: April 16, 2026, 11:32 a.m.