Triple
T15008523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | They Came Together |
E377772
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Matt Novack |
E1052407
|
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: Matt Novack | Statement: [They Came Together, musicBy, Matt Novack]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Novack Context triple: [They Came Together, musicBy, Matt Novack]
-
A.
Matt Novack
chosen
Matt Novack is a film and television composer best known for scoring the Netflix series "GLOW."
-
B.
Matt DeRoss
Matt DeRoss is a film producer best known for his work on the critically acclaimed drama "The End of the Tour."
-
C.
Michael Nolin
Michael Nolin is an American film producer best known for his work on the acclaimed music drama "Mr. Holland's Opus."
-
D.
Blaine Novak
Blaine Novak is an American filmmaker, actor, and screenwriter best known for his work on independent films such as "They All Laughed" and "Stranger Than Paradise."
-
E.
Matt Nable
Matt Nable is an Australian actor, writer, and former professional rugby league player known for roles in film and television, including genre series and crime dramas.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded73348d4819091d9e7f1b0fed822 |
completed | April 15, 2026, 12:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff908410548190ada5d4f71d52919b |
completed | May 9, 2026, 7:52 p.m. |
Created at: April 10, 2026, 2:55 a.m.