Triple
T8841650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rolling in the Deep |
E210401
|
entity |
| Predicate | musicVideoDirector |
P4911
|
FINISHED |
| Object | Sam Brown |
E140112
|
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: Sam Brown | Statement: [Rolling in the Deep, musicVideoDirector, Sam Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sam Brown Context triple: [Rolling in the Deep, musicVideoDirector, Sam Brown]
-
A.
Sam Brown
chosen
Sam Brown is a British music video director known for creating visually distinctive videos for artists such as James Blunt, including the hit song "You're Beautiful."
-
B.
Sam Brown
Sam Brown is a musician best known for being a member of the blues-rock supergroup Derek and the Dominos.
-
C.
Kay Brown
Kay Brown was the wife of renowned Canadian jazz trumpeter and bandleader Maynard Ferguson.
-
D.
Andrew Brown
Andrew Brown is a songwriter credited with co-writing the track "Stop and Stare."
-
E.
Beth Brown
Beth Brown is a screenwriter known for her work on the film "Applause."
- 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_69ca838967bc8190b46c3c80a2887ea4 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60876c6c8190b1b490e447e1cf4b |
completed | April 1, 2026, 12:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf89a41a2c8190b69e5a1b157f9325 |
completed | April 3, 2026, 9:34 a.m. |
Created at: March 30, 2026, 6:48 p.m.