Triple
T8690614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benny Benassi |
E206277
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | Kelis |
E35644
|
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: Kelis | Statement: [Benny Benassi, associatedAct, Kelis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kelis Context triple: [Benny Benassi, associatedAct, Kelis]
-
A.
Kelis
chosen
Kelis is an American singer, songwriter, and chef best known for her eclectic R&B and hip-hop-influenced music, including the hit single "Milkshake."
-
B.
Keyshia Cole
Keyshia Cole is an American R&B singer, songwriter, and television personality known for her soulful vocals and hit albums in the 2000s.
-
C.
Keri Hilson
Keri Hilson is an American singer, songwriter, and actress known for her R&B and pop hits as well as her work writing songs for other major artists.
-
D.
Christina Milian
Christina Milian is an American singer, songwriter, and actress known for early-2000s R&B-pop hits like "Dip It Low" and roles in films such as "Love Don't Cost a Thing."
-
E.
Ashanti
Ashanti is an American R&B singer and songwriter who rose to fame in the early 2000s with hits like "Foolish" and her self-titled debut album.
- 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_69ca835481fc819084e33d3bc883bfa6 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5735ffdc819094126e2698f98511 |
completed | March 31, 2026, 11:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b12e42e48190b62b772d150117f2 |
completed | April 4, 2026, 6:35 a.m. |
Created at: March 30, 2026, 6:33 p.m.