Triple
T8424395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dirty Dancing |
E198940
|
entity |
| Predicate | storyBy |
P1955
|
FINISHED |
| Object | Eleanor Bergstein |
E733163
|
NE FINISHED |
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: Eleanor Bergstein | Statement: [Dirty Dancing, storyBy, Eleanor Bergstein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eleanor Bergstein Context triple: [Dirty Dancing, storyBy, Eleanor Bergstein]
-
A.
Eleanor Bergstein
chosen
Eleanor Bergstein is an American writer and filmmaker best known for creating and writing the hit 1987 romantic drama film "Dirty Dancing."
-
B.
Patricia P. Frank
Patricia P. Frank is a screenwriter known for her work on the classic comedy film "The Court Jester."
-
C.
Miriam Karlin
Miriam Karlin was a British actress and comedian best known for her sharp-tongued, working-class roles in mid-20th-century film and television.
-
D.
Barbara Guggenheim
Barbara Guggenheim is a member of the prominent Guggenheim family, known for its significant influence in art patronage and philanthropy.
-
E.
Barbara Bosson
Barbara Bosson was an American actress best known for her Emmy-nominated role as Fay Furillo on the groundbreaking police drama "Hill Street Blues."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca8312d63c8190bf133b676b44a385 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb85a0d04481908a5da908cafeceaa |
completed | March 31, 2026, 8:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1d502c448190aabc957786bde79f |
completed | April 2, 2026, 7:40 a.m. |
Created at: March 30, 2026, 6:07 p.m.