Triple
T4987787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kelly Rowland |
E112045
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | Nelly |
E17165
|
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: Nelly | Statement: [Kelly Rowland, associatedAct, Nelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nelly Context triple: [Kelly Rowland, associatedAct, Nelly]
-
A.
Nelly
chosen
Nelly is an American rapper, singer, and songwriter known for early-2000s hits like "Hot in Herre" and "Dilemma."
-
B.
Lil Wayne
Lil Wayne is a Grammy-winning American rapper, singer, and songwriter known for his influential role in hip-hop and prolific output since the late 1990s.
-
C.
John Rich
John Rich was an influential 18th-century English theatre manager and producer, best known for pioneering English pantomime and helping establish Covent Garden as a major London playhouse.
-
D.
Big Boi
Big Boi is an American rapper, songwriter, and producer best known as one half of the influential hip hop duo Outkast.
-
E.
T-Pain
T-Pain is an American singer, rapper, and producer known for popularizing the creative use of Auto-Tune in mainstream hip-hop and R&B music.
- 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_69bd441be7bc8190b530362d427b97d2 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd727d473c8190beea66bf11a826e3 |
completed | March 20, 2026, 4:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be9c31748c81909477e01261b5a78a |
completed | March 21, 2026, 1:25 p.m. |
Created at: March 20, 2026, 1:34 p.m.