Triple
T15939458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pound Cake / Paris Morton Music 2 |
E386520
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Jordan Evans |
E1187420
|
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: Jordan Evans | Statement: [Pound Cake / Paris Morton Music 2, writer, Jordan Evans]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jordan Evans Context triple: [Pound Cake / Paris Morton Music 2, writer, Jordan Evans]
-
A.
Jordan Evans
Jordan Evans is a notable alumnus of Norman North High School, recognized for his achievements after graduating from the school.
-
B.
Jordan Evans
chosen
Jordan Evans is a Canadian hip-hop and R&B record producer known for his work with artists such as Drake.
-
C.
Jordan Evans
Jordan Evans is a songwriter best known for co-writing Eminem’s hit single "Not Afraid."
-
D.
Lee Evans
Lee Evans is a British stand-up comedian and actor known for his high-energy, physical comedy and roles in films such as "Funny Bones" and "There's Something About Mary."
-
E.
Natalie Evans
Natalie Evans was the wife of Pulitzer Prize–winning American editorial cartoonist Bill Mauldin.
- 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_69d86da750008190987eb26be3f6c118 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156ad9988819089ad7822e0f46177 |
completed | April 16, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffcf14ab088190b1d2f1f6b18bf85d |
completed | May 10, 2026, 12:19 a.m. |
Created at: April 10, 2026, 4:53 a.m.