Triple
T18601570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frederick Wiseman |
E454631
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Wiseman |
—
|
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: Wiseman | Statement: [Frederick Wiseman, familyName, Wiseman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wiseman Context triple: [Frederick Wiseman, familyName, Wiseman]
-
A.
Wiseman
chosen
Wiseman is a surname most notably associated with Canadian actor Joseph Wiseman, who famously portrayed the title villain in the first James Bond film, "Dr. No."
-
B.
Wellman
Wellman is a surname most notably associated with William A. Wellman, an influential American film director of early Hollywood cinema.
-
C.
Wisemen
"Wisemen" is a song by British singer-songwriter James Blunt, featured on his debut studio album "Back to Bedlam."
-
D.
Davidman
Davidman is a surname most notably associated with Joy Davidman, the American poet and writer who became the wife of C. S. Lewis.
-
E.
No-Man
No-Man is a British art-pop and ambient rock band known for its atmospheric soundscapes and emotionally introspective songwriting.
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5475112608190acacc5ac7a08c4a0 |
completed | April 19, 2026, 9:21 p.m. |
Created at: April 10, 2026, 11:45 a.m.