Triple
T17341987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saturday Night Fever |
E421087
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Norman Wexler |
E948180
|
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: Norman Wexler | Statement: [Saturday Night Fever, screenwriter, Norman Wexler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Norman Wexler Context triple: [Saturday Night Fever, screenwriter, Norman Wexler]
-
A.
Norman Wexler
chosen
Norman Wexler was an American screenwriter best known for his work on influential 1970s films such as "Serpico" and "Saturday Night Fever."
-
B.
Milton J. Rosenberg
Milton J. Rosenberg was an American social psychologist and long-time Chicago radio talk show host known for his influential program "Extension 720."
-
C.
Sidney B. Kramer
Sidney B. Kramer was an American publisher best known as a co-founder of the mass-market paperback company Bantam Books.
-
D.
Melvin Weinberg
Melvin Weinberg was a con artist turned FBI informant who played a central role in orchestrating the ABSCAM political corruption sting operation in the late 1970s.
-
E.
Marvin L. Cohen
Marvin L. Cohen is a prominent American condensed matter physicist known for his pioneering work in computational materials science and electronic structure theory.
- 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_69d889d3adc881909319f1edb8d2a956 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a173e1c8190afcebf25ee902cc8 |
completed | April 19, 2026, 2:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a018c588a7081909ab108cb4adfedfe |
completed | May 11, 2026, 7:59 a.m. |
Created at: April 10, 2026, 5:44 a.m.