Triple
T22427398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Room |
E554407
|
entity |
| Predicate | producedBy |
P490
|
FINISHED |
| Object | Ed Guiney |
—
|
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: Ed Guiney | Statement: [Room, producedBy, Ed Guiney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ed Guiney Context triple: [Room, producedBy, Ed Guiney]
-
A.
Ed Guiney
chosen
Ed Guiney is an Irish film producer and co-founder of Element Pictures, known for collaborating on acclaimed films such as "The Favourite," "Room," and "Poor Things."
-
B.
Michael Boughen
Michael Boughen is a film producer known for his work on action and thriller movies, including the Jason Statham–starring film "Killer Elite."
-
C.
Stephen Vail
Stephen Vail was a prominent early 19th-century American industrialist and ironworks owner in New Jersey, best known as the father of telegraph pioneer Alfred Vail.
-
D.
Jeffrey Squires
Jeffrey Squires is an individual known primarily in a professional or academic context under the title Dr. Jeffrey Squires.
-
E.
Michael Bentt
Michael Bentt is a former British-American professional heavyweight boxer who briefly held the WBO world title before becoming an actor and boxing consultant in film and television.
- 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_69e11e4f2d0c819091aa3558ea2ee630 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15a2e438481908d43026727afa709 |
completed | April 29, 2026, 1:09 a.m. |
Created at: April 16, 2026, 8:47 p.m.