Triple
T22673371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Friends |
E560279
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Jonathan Firth |
—
|
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: Jonathan Firth | Statement: [American Friends, hasCastMember, Jonathan Firth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jonathan Firth Context triple: [American Friends, hasCastMember, Jonathan Firth]
-
A.
Jonathan Firth
chosen
Jonathan Firth is a British actor known for his work in film, television, and theatre, including period dramas and literary adaptations.
-
B.
Neville Bamber
Neville Bamber was the husband of renowned British psychotherapist and human rights activist Helen Bamber.
-
C.
Lewis MacDougall
Lewis MacDougall is a Scottish actor best known for his breakout role as the young protagonist in the fantasy drama film "A Monster Calls."
-
D.
Alfred Enoch
Alfred Enoch is a British actor best known for playing Wes Gibbins in the television series "How to Get Away with Murder" and appearing as Dean Thomas in the "Harry Potter" film franchise.
-
E.
Ross Helford
Ross Helford is a screenwriter best known for his work on the erotic thriller film "Wild Things 2."
- 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_69e2454bfd00819099115715a22cb057 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17821daf88190b18a73a222fc22fb |
completed | April 29, 2026, 3:16 a.m. |
Created at: April 17, 2026, 3:10 p.m.