Triple
T20148680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Both of Us |
E491375
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Cirkut |
—
|
NE NERFINISHED |
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: Cirkut | Statement: [Both of Us, writer, Cirkut]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cirkut Context triple: [Both of Us, writer, Cirkut]
-
A.
Cirkut
chosen
Cirkut is a Canadian record producer and songwriter best known for crafting chart-topping pop hits for artists like Katy Perry, The Weeknd, and Miley Cyrus.
-
B.
Braison Cyrus
Braison Cyrus is an American actor, model, and musician best known as a member of the Cyrus entertainment family.
-
C.
Robert Levon Been
Robert Levon Been is an American musician and songwriter best known as the bassist and co-vocalist of the alternative rock band Black Rebel Motorcycle Club.
-
D.
Corbin Bleu
Corbin Bleu is an American actor, singer, and dancer best known for his breakout role in Disney Channel’s High School Musical franchise and subsequent work in film, television, and theater.
-
E.
Taio Cruz
Taio Cruz is a British singer, songwriter, and record producer best known for his international pop and dance hits like "Dynamite" and "Break Your Heart."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da6265f8f0819080b29c752a574088 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e667a0075c8190a5c4de53a0caa7f6 |
completed | April 20, 2026, 5:51 p.m. |
Created at: April 11, 2026, 11:33 p.m.