Triple
T13931045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mustard |
E334990
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | Ella Mai |
E410874
|
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: Ella Mai | Statement: [Mustard, associatedAct, Ella Mai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ella Mai Context triple: [Mustard, associatedAct, Ella Mai]
-
A.
Ella Mai
chosen
Ella Mai is a British R&B singer and songwriter best known for her hit single "Boo'd Up" and her self-titled debut studio album.
-
B.
Ella Carey
Ella Carey is known primarily as the daughter of American actor Harry Carey.
-
C.
H.E.R.
H.E.R. is an American R&B singer-songwriter and multi-instrumentalist known for her soulful vocals, introspective lyrics, and Grammy-winning work.
-
D.
Elodie Yung
Elodie Yung is a French actress best known for her roles in projects like Marvel's "Daredevil" and "The Defenders," where she portrayed the assassin Elektra Natchios.
-
E.
Jazmine Sullivan
Jazmine Sullivan is an American R&B and soul singer-songwriter renowned for her powerful vocals and critically acclaimed albums such as "Fearless" and "Heaux Tales."
- 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_69d81c5f739081908bc05b2461f54828 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2cf13b2881908a48058a719d3745 |
completed | April 14, 2026, 12:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7ce8452648190b7392d75eb1ca874 |
completed | May 3, 2026, 10:39 p.m. |
Created at: April 9, 2026, 10:16 p.m.