Triple
T21133464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dorcon |
E520747
|
entity |
| Predicate | contrastsWith |
P278
|
FINISHED |
| Object | Daphnis |
—
|
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: Daphnis | Statement: [Dorcon, contrastsWith, Daphnis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daphnis Context triple: [Dorcon, contrastsWith, Daphnis]
-
A.
Daphnis
chosen
Daphnis is a young shepherd and one of the two pastoral lovers at the center of the ancient Greek romance "Daphnis and Chloe."
-
B.
Daphnis
Daphnis is a small moon of Saturn that orbits within the planet’s rings and gravitationally sculpts the edges of the Keeler Gap.
-
C.
Sophillus
Sophillus was the father of the ancient Greek tragedian Sophocles, about whom little is known beyond his paternal connection to the playwright.
-
D.
Leontine
Leontine is a feminine given name, used as a variant of names like Leona and Leontina, with roots in Latin meaning "lion-like" or "lioness."
-
E.
Ousanas
Ousanas was a king of the ancient Kingdom of Aksum in what is now Ethiopia, known from inscriptions and coinage as an early Christian-era ruler preceding King Ezana.
- 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_69e0b50b53048190ae34e8abbe3c5ada |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7235847948190984c7009ca7f6189 |
completed | April 21, 2026, 7:12 a.m. |
Created at: April 16, 2026, 2:56 p.m.