Triple
T20379493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cassia |
E497783
|
entity |
| Predicate | hasVariantSpelling |
P457
|
FINISHED |
| Object | Kassia |
—
|
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: Kassia | Statement: [Cassia, hasVariantSpelling, Kassia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kassia Context triple: [Cassia, hasVariantSpelling, Kassia]
-
A.
Kassia
chosen
Kassia was a 9th-century Byzantine abbess, poet, and hymnographer renowned as one of the earliest and most important female composers in the Eastern Orthodox tradition.
-
B.
Cassia
Cassia is a feminine given name used in various cultures, often associated with warmth and spice due to its connection to the cassia tree and cinnamon.
-
C.
Cassia Longina
Cassia Longina was the daughter of Roman Empress Domitia Longina and thus a member of the Flavian imperial family in 1st-century Rome.
-
D.
Euphrasie
Euphrasie is the birth name of Cosette, the tragic orphaned girl who becomes a central character in Victor Hugo's novel "Les Misérables."
-
E.
Kastania
Kastania is a small settlement in Greece located near the area of Kyllini in the western Peloponnese.
- 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_69e0b4a5b7908190a972e4e7e698ae94 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678af651c8190b4922294a937e699 |
completed | April 20, 2026, 7:04 p.m. |
Created at: April 16, 2026, 11:27 a.m.