Triple
T16910080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Death to Smoochy |
E410170
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | David Newman |
E82519
|
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: David Newman | Statement: [Death to Smoochy, composer, David Newman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Newman Context triple: [Death to Smoochy, composer, David Newman]
-
A.
David Newman
chosen
David Newman is an American film composer known for scoring numerous Hollywood movies and continuing the Newman family’s influential legacy in film music.
-
B.
David Newman
David Newman was an American screenwriter best known for co-writing influential films of the 1960s and 1970s, including the landmark crime drama "Bonnie and Clyde."
-
C.
Mack David
Mack David was an American lyricist and songwriter known for his popular song adaptations and contributions to film and television music.
-
D.
Carl Sigman
Carl Sigman was an American songwriter and lyricist known for penning the words to numerous popular standards across mid-20th-century music.
-
E.
Harold Rome
Harold Rome was an American composer and lyricist best known for his work on Broadway musicals and film scores in the mid-20th century.
- 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_69d886c7b1e481908c3766dfa8c13458 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3ca3ca0c481909ff361ccf4a922e3 |
completed | April 18, 2026, 6:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c7b98d5c8190b61de47b246549e3 |
completed | May 10, 2026, 6 p.m. |
Created at: April 10, 2026, 5:30 a.m.