Triple
T23268745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arian |
E588230
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Ariane |
—
|
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: Ariane | Statement: [Arian, hasVariant, Ariane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ariane Context triple: [Arian, hasVariant, Ariane]
-
A.
Ariane
Ariane is the alternate title of the 1957 romantic comedy film "Love in the Afternoon," directed by Billy Wilder and starring Audrey Hepburn and Gary Cooper.
-
B.
Ariane
chosen
Ariane is a Dutch princess, the youngest daughter of King Willem-Alexander and Queen Máxima of the Netherlands.
-
C.
Rosetta
"Rosetta" is a classic jazz standard composed by pianist Earl Hines that has become a staple of the swing and traditional jazz repertoire.
-
D.
Rosetta
Rosetta is a feminine given name of Latin origin, often considered a diminutive of "Rosa" and associated with meanings related to "little rose."
-
E.
Rosetta
Rosetta is a small rural settlement in the KwaZulu-Natal Midlands of South Africa, known for its scenic countryside and proximity to popular tourist routes.
- 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_69e25d148adc819088efbf42672604e9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1957219188190b30bceffad1542da |
completed | April 29, 2026, 5:21 a.m. |
Created at: April 17, 2026, 4:43 p.m.