Triple
T20467071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sophie Vavasseur |
E502078
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Reign |
—
|
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: Reign | Statement: [Sophie Vavasseur, notableWork, Reign]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Reign Context triple: [Sophie Vavasseur, notableWork, Reign]
-
A.
Reign
Reign is a studio album by Ghanaian dancehall artist Shatta Wale that helped solidify his prominence in the African music scene.
-
B.
Reign
chosen
Reign is a historical drama television series that follows the early life and political struggles of Mary, Queen of Scots, at the French court.
-
C.
Reign
Reign is a given name notably borne by Reign Aston Disick, the son of Kourtney Kardashian and Scott Disick.
-
D.
Reign
Reign is a professional American women's soccer team competing in the National Women's Soccer League and based in the Seattle metropolitan area.
-
E.
La Reine de la couronne
La Reine de la couronne is a dramatic work by French playwright Marcelle Maurette, best known for her historical and psychologically driven stage pieces.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6995d9d1c81909ee223a35a0850ba |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.