Triple
T2008506
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Jackson |
E43639
|
entity |
| Predicate | genre |
P14
|
FINISHED |
| Object | R&B |
E11089
|
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: R&B | Statement: [Michael Jackson, genre, R&B]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: R&B Context triple: [Michael Jackson, genre, R&B]
-
A.
R&B
chosen
R&B is a popular music genre that blends soulful vocals with rhythmic grooves, drawing from blues, jazz, gospel, and later funk and hip-hop influences.
-
B.
Soul
Soul is a 2020 Pixar animated film that explores themes of purpose, passion, and the afterlife through the story of a jazz musician who experiences a life-changing journey beyond Earth.
-
C.
Soul
"Soul" is a studio album by American rock band Seal that showcases his distinctive blend of pop, R&B, and soul through covers of classic soul songs.
-
D.
Pop
Pop is U2’s 1997 studio album that blends alternative rock with electronic and dance influences, reflecting the band’s experimental phase in the late 1990s.
-
E.
US Hot R&B/Hip-Hop Songs
US Hot R&B/Hip-Hop Songs is a Billboard music chart that ranks the most popular R&B and hip-hop songs in the United States based on sales, radio airplay, and streaming data.
- 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_69a88716e9f08190946313fdc949e3cf |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb89aca908190b8b659af65afdf6f |
completed | March 7, 2026, 5:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae0ae395a08190abf2077ad7a975ba |
completed | March 8, 2026, 11:48 p.m. |
Created at: March 4, 2026, 7:37 p.m.