Triple
T5043429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Come On |
E113600
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Paul Dunlap |
E488977
|
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: Paul Dunlap | Statement: [The Come On, musicBy, Paul Dunlap]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Dunlap Context triple: [The Come On, musicBy, Paul Dunlap]
-
A.
Paul Dunlap
chosen
Paul Dunlap was an American film composer known for scoring numerous mid-20th-century movies, particularly in the crime, horror, and Western genres.
-
B.
Andrew Dunlap
Andrew Dunlap is a voice actor known for portraying Prince Charming in animated media.
-
C.
Frank Barnwell
Frank Barnwell was a British aeronautical engineer and aircraft designer best known for creating several important World War I and interwar aircraft for the Bristol Aeroplane Company.
-
D.
Charles Roane
Charles Roane is a music producer known for his work on the album "Back to Basics."
-
E.
Horace Cleveland
Horace Cleveland was a prominent 19th-century American landscape architect known for designing parks, cemeteries, and urban green spaces across the United States.
- 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_69bd44391fc48190a311ce9c826c209b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73fc04f08190aba851fa0192d0fb |
completed | March 20, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beb0f746788190bf73b8b5069e89cb |
completed | March 21, 2026, 2:53 p.m. |
Created at: March 20, 2026, 1:37 p.m.