Triple
T20388279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fright Night |
E498014
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Brad Fiedel |
—
|
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: Brad Fiedel | Statement: [Fright Night, musicBy, Brad Fiedel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brad Fiedel Context triple: [Fright Night, musicBy, Brad Fiedel]
-
A.
Brad Fiedel
chosen
Brad Fiedel is an American composer best known for his synthesizer-driven film scores, including the iconic music for "The Terminator" series.
-
B.
Albert Weinert
Albert Weinert was a German-American sculptor and monument designer known for his public memorials in the United States.
-
C.
John Debney
John Debney is an American film composer known for scoring a wide range of movies and television shows, including major studio productions and acclaimed dramas.
-
D.
Martin O'Donnell
Martin O'Donnell is an American composer best known for creating the iconic music of the Halo video game series.
-
E.
Harry Gregson-Williams
Harry Gregson-Williams is a British composer best known for his film and video game scores, including work on the "Shrek" series, "The Chronicles of Narnia," and the "Metal Gear Solid" franchise.
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6790d9e5881908bde7da9e5e541a0 |
completed | April 20, 2026, 7:05 p.m. |
Created at: April 16, 2026, 11:28 a.m.