Triple
T22379680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Potion |
E553237
|
entity |
| Predicate | artist |
P184
|
FINISHED |
| Object | Dua Lipa |
—
|
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: Dua Lipa | Statement: [Potion, artist, Dua Lipa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dua Lipa Context triple: [Potion, artist, Dua Lipa]
-
A.
Dua Lipa
chosen
Dua Lipa is a British-Albanian pop singer and songwriter known for her deep, distinctive voice and chart-topping hits like "New Rules" and "Don't Start Now."
-
B.
Tulisa Contostavlos
Tulisa Contostavlos is a British singer, songwriter, and television personality best known as a member of the hip hop group N-Dubz and as a former judge on The X Factor UK.
-
C.
Ann-Marie
Ann-Marie is the protagonist of the novel "Eat My Heart Out," a young woman navigating chaotic relationships and identity in contemporary London.
-
D.
Ella Carey
Ella Carey is known primarily as the daughter of American actor Harry Carey.
-
E.
Anne-Marie
Anne-Marie is an English pop singer and songwriter known for hits like "Alarm" and "2002" and for serving as a coach on The Voice UK.
- 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_69e11e4c03248190a26a5060ea6973ee |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1582afe6c819093940f9d817c64a8 |
completed | April 29, 2026, 1 a.m. |
Created at: April 16, 2026, 8:45 p.m.