Triple
T13415626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary |
E313204
|
entity |
| Predicate | artist |
P184
|
FINISHED |
| Object | Sarkodie |
E62563
|
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: Sarkodie | Statement: [Mary, artist, Sarkodie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarkodie Context triple: [Mary, artist, Sarkodie]
-
A.
Sarkodie
chosen
Sarkodie is a renowned Ghanaian rapper and songwriter celebrated as one of Africa’s leading hip-hop and Afrobeats artists.
-
B.
Skepta
Skepta is a British grime MC, rapper, and producer known for pioneering the UK grime scene and achieving international success with hits like "Shutdown" and "That's Not Me."
-
C.
Pleasure P
Pleasure P is an American R&B singer and former member of the group Pretty Ricky, known for his smooth vocals and solo hits in the late 2000s.
-
D.
Peedi Crakk
Peedi Crakk is an American rapper from Philadelphia known for his work with State Property and Roc-A-Fella Records in the early 2000s.
-
E.
Wale
Wale is an American rapper and songwriter known for his witty wordplay, poetic lyricism, and hits like "Lotus Flower Bomb" and "Bad."
- 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_69d806ad0c44819088833ae1ec9e9690 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaeb6e904819098cc9153fd2feaf5 |
completed | April 12, 2026, 2:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd27f0e59c8190b40213e999c75feb |
completed | May 8, 2026, 12:01 a.m. |
Created at: April 9, 2026, 9:39 p.m.