Triple
T22230004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unbroken |
E549440
|
entity |
| Predicate | featuresArtist |
P1952
|
FINISHED |
| Object | Iyaz |
—
|
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: Iyaz | Statement: [Unbroken, featuresArtist, Iyaz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Iyaz Context triple: [Unbroken, featuresArtist, Iyaz]
-
A.
Iyaz
chosen
Iyaz is a British Virgin Islands singer and songwriter best known for his 2009 international hit single "Replay" and his work in the pop and R&B genres.
-
B.
Zubeen
Zubeen is a given name, typically used as a variant spelling of the name Zubin.
-
C.
Tanishk Bagchi
Tanishk Bagchi is an Indian music composer and producer known for his work on numerous Bollywood film soundtracks and popular song remixes.
-
D.
Mahmood
Mahmood is a masculine given name of Arabic origin, commonly used in various Muslim-majority cultures and often spelled in multiple variants such as Mahmoud or Mahmud.
-
E.
Badshah
Badshah is an imperial title historically used by Mughal emperors and other Muslim sovereigns in South Asia to denote supreme rulership.
- 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bf173308190a3d21bfc59b39728 |
completed | April 28, 2026, 9:51 p.m. |
Created at: April 16, 2026, 8:37 p.m.