Triple
T19426131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Knock on Wood |
E485984
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Melvin Frank |
—
|
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: Melvin Frank | Statement: [Knock on Wood, director, Melvin Frank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Melvin Frank Context triple: [Knock on Wood, director, Melvin Frank]
-
A.
Melvin Frank
chosen
Melvin Frank was an American screenwriter, producer, and director best known for his work on classic mid-20th-century comedies.
-
B.
Melvin Schlein
Melvin Schlein is the father of Italian politician Elly Schlein.
-
C.
Melvin Simon
Melvin Simon was an American real estate developer and businessman best known as a co-founder of the major shopping mall company Simon Property Group.
-
D.
Melvin Goodman
Melvin Goodman is an American former CIA analyst, author, and national security expert known for his outspoken criticism of U.S. intelligence practices and foreign policy.
-
E.
Louis Garfinkle
Louis Garfinkle was an American screenwriter best known for co-writing the acclaimed Vietnam War drama film "The Deer Hunter."
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63218772c8190a48b6cb01bd12b73 |
completed | April 20, 2026, 2:03 p.m. |
Created at: April 10, 2026, 1:37 p.m.