Triple
T3138186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bruno Mars |
E65582
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
24K Magic
24K Magic is a funk- and R&B-infused studio album by Bruno Mars known for its retro sound and hit singles like "24K Magic" and "That's What I Like."
|
E329493
|
NE FINISHED |
How this triple was built (4 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: 24K Magic | Statement: [Bruno Mars, notableWork, 24K Magic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 24K Magic Context triple: [Bruno Mars, notableWork, 24K Magic]
-
A.
Get on Up
Get on Up is a 2014 biographical drama film about the life and career of soul music legend James Brown.
-
B.
Wyldstyle
Wyldstyle is a rebellious and resourceful Master Builder who plays a leading role in The Lego Movie’s fight against conformity and tyranny.
-
C.
Can't Stop the Feeling!
"Can't Stop the Feeling!" is a 2016 upbeat pop song by Justin Timberlake, known for its feel-good dance vibe and association with the animated film Trolls.
-
D.
Got to Give It Up
"Got to Give It Up" is a 1977 funk and disco-influenced hit song by Marvin Gaye known for its infectious groove and party atmosphere.
-
E.
Get Up
"Get Up" is a track by the American heavy metal band Scream, featured on one of their releases.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: 24K Magic Triple: [Bruno Mars, notableWork, 24K Magic]
Generated description
24K Magic is a funk- and R&B-infused studio album by Bruno Mars known for its retro sound and hit singles like "24K Magic" and "That's What I Like."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 24K Magic Target entity description: 24K Magic is a funk- and R&B-infused studio album by Bruno Mars known for its retro sound and hit singles like "24K Magic" and "That's What I Like."
-
A.
Hotline Bling
"Hotline Bling" is a 2015 Drake hit single known for its minimalist production, viral music video, and widespread cultural impact.
-
B.
Get on Up
Get on Up is a 2014 biographical drama film about the life and career of soul music legend James Brown.
-
C.
Wyldstyle
Wyldstyle is a rebellious and resourceful Master Builder who plays a leading role in The Lego Movie’s fight against conformity and tyranny.
-
D.
Can't Stop the Feeling!
"Can't Stop the Feeling!" is a 2016 upbeat pop song by Justin Timberlake, known for its feel-good dance vibe and association with the animated film Trolls.
-
E.
Got to Give It Up
"Got to Give It Up" is a 1977 funk and disco-influenced hit song by Marvin Gaye known for its infectious groove and party atmosphere.
- F. None of above. chosen
Provenance (5 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_69ad8581c25c8190b0d85ba9b9baa531 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada574509c81908a88bb10ea35516d |
completed | March 8, 2026, 4:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b20f8a1a2081909081c36075d4ddbe |
completed | March 12, 2026, 12:57 a.m. |
| NEDg | Description generation | batch_69b2137b30508190a5a9a439d77ae3bb |
completed | March 12, 2026, 1:14 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b21413338c8190997d0f2f11f41008 |
completed | March 12, 2026, 1:17 a.m. |
Created at: March 8, 2026, 3:05 p.m.