Triple
T2010931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince |
E43685
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | Chaka Khan |
E10630
|
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: Chaka Khan | Statement: [Prince, associatedAct, Chaka Khan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chaka Khan Context triple: [Prince, associatedAct, Chaka Khan]
-
A.
Chaka Khan
chosen
Chaka Khan is an American singer known as the "Queen of Funk," celebrated for her powerful vocals and influential work in funk, R&B, and soul music since the 1970s.
-
B.
Patrice Rushen
Patrice Rushen is an American jazz and R&B pianist, singer, composer, and record producer best known for her 1982 hit song "Forget Me Nots."
-
C.
Ledisi
Ledisi is a Grammy-winning American R&B and jazz singer, songwriter, and actress known for her powerful vocals and soulful, genre-blending style.
-
D.
Yolanda Adams
Yolanda Adams is an American gospel singer, radio host, and actress renowned for her powerful vocals and influential contemporary gospel recordings.
-
E.
Queen Latifah
Queen Latifah is an American rapper, singer, actress, and producer known as one of the pioneering women in hip-hop and a prominent figure in film and television.
- 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_69abb8b150a8819096c919465fd91ab5 |
completed | March 7, 2026, 5:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae0ae85ed48190adc75fd17b17f6c9 |
completed | March 8, 2026, 11:48 p.m. |
Created at: March 4, 2026, 7:37 p.m.