Triple
T18233324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lose to Win |
E436600
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Emeli Sandé |
—
|
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: Emeli Sandé | Statement: [Lose to Win, writer, Emeli Sandé]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emeli Sandé Context triple: [Lose to Win, writer, Emeli Sandé]
-
A.
Emeli Sandé
chosen
Emeli Sandé is a Scottish singer-songwriter known for her powerful vocals and soulful pop hits such as "Next to Me" and "Read All About It."
-
B.
Ellie Goulding
Ellie Goulding is an English singer-songwriter known for her ethereal vocals and synth-pop hits such as "Lights" and "Love Me Like You Do."
-
C.
Paloma Faith
Paloma Faith is an English singer, songwriter, and actress known for her soulful retro-inspired music and distinctive theatrical style.
-
D.
Jess Glynne
Jess Glynne is an English singer and songwriter known for her soulful vocals and chart-topping pop and dance hits, including several UK number-one singles.
-
E.
Leona Lewis
Leona Lewis is a British singer and songwriter who rose to fame after winning The X Factor and is best known for her powerful vocals and hit single "Bleeding Love."
- 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_69d8b9103a8081908bbb0836fef10efd |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4f4b512a88190aa493b0793ab28b3 |
completed | April 19, 2026, 3:28 p.m. |
Created at: April 10, 2026, 10:33 a.m.