Triple
T8112997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Murda Beatz |
E189400
|
entity |
| Predicate | hasCollaboratedWith |
P8554
|
FINISHED |
| Object | Drake |
E65589
|
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: Drake | Statement: [Murda Beatz, hasCollaboratedWith, Drake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drake Context triple: [Murda Beatz, hasCollaboratedWith, Drake]
-
A.
Drake
chosen
Drake is a Canadian rapper, singer, and songwriter who became one of the most commercially successful and influential hip-hop and pop artists of the 21st century.
-
B.
Drake
Drake is the nickname of Enzo Ferrari, the legendary Italian founder of the Ferrari automobile marque and racing team.
-
C.
Drake
Drake is the primary vampire antagonist in the film "Blade: Trinity," depicted as an ancient and powerful progenitor of the vampire race.
-
D.
The Weeknd
The Weeknd is a Canadian singer, songwriter, and producer known for his dark, atmospheric R&B sound and globally successful hits like “Blinding Lights” and “Starboy.”
-
E.
Jacquees
Jacquees is an American R&B singer and songwriter known for his smooth vocal style, mixtapes, and the hit single "B.E.D."
- 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_69ca82baad008190ab2859712b9b1607 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb432d7dfc8190b9c980f32c7b4623 |
completed | March 31, 2026, 3:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc93b18a6c81908a3a4bc25552d97b |
completed | April 1, 2026, 3:40 a.m. |
Created at: March 30, 2026, 5:32 p.m.