Triple
T19771673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indian Summer |
E474902
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Miles Goodman |
—
|
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: Miles Goodman | Statement: [Indian Summer, musicBy, Miles Goodman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miles Goodman Context triple: [Indian Summer, musicBy, Miles Goodman]
-
A.
Miles Goodman
chosen
Miles Goodman was an American composer and jazz record producer best known for his film scores, particularly for popular comedies of the 1980s and early 1990s.
-
B.
Miles Blume
Miles Blume is the disturbed young boy at the center of the 2019 horror film "The Prodigy," whose unsettling behavior drives the movie's supernatural thriller plot.
-
C.
Miles Fairley
Miles Fairley is a charming but duplicitous children's book author who becomes a romantic interest of the protagonist in the classic film "The Ghost and Mrs. Muir."
-
D.
Miles Morgan
Miles Morgan is a member of the prominent Morgan banking family, known primarily as a descendant of financier Henry Sturgis Morgan.
-
E.
Miles Tuck
Miles Tuck is a character in the novel "Tuck Everlasting," a member of the immortal Tuck family who grapples with the consequences of eternal life.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6535bd8c0819097671783962b6bc5 |
completed | April 20, 2026, 4:25 p.m. |
Created at: April 10, 2026, 1:48 p.m.