Triple
T22596417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isadora |
E574693
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Raymond Stross |
—
|
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: Raymond Stross | Statement: [Isadora, producer, Raymond Stross]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Raymond Stross Context triple: [Isadora, producer, Raymond Stross]
-
A.
Raymond Stross
chosen
Raymond Stross was a British film producer active in the mid-20th century, known for backing a range of dramas and genre films.
-
B.
John Buckwalter
John Buckwalter is an actor known for his role in Woody Allen’s mockumentary film "Zelig."
-
C.
Leland Robinson
Leland Robinson is the son of influential music producer and Sugar Hill Records co-founder Sylvia Robinson.
-
D.
Cornelius Riordan
Cornelius Riordan is a person notable enough to be specifically cited as a bearer of the surname Riordan.
-
E.
Alan E. Nourse
Alan E. Nourse was an American science fiction author and physician known for works that often explored medical and social themes, including the novel "The Bladerunner."
- 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_69e245bc11308190b69d794d5d1e0bb6 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f16269a56881909bb5af0258150f93 |
completed | April 29, 2026, 1:44 a.m. |
Created at: April 17, 2026, 2:50 p.m.