Triple
T19070306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spyridon Samaras |
E466772
|
entity |
| Predicate | composed |
P1142
|
FINISHED |
| Object | Flora mirabilis |
—
|
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: Flora mirabilis | Statement: [Spyridon Samaras, composed, Flora mirabilis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Flora mirabilis Context triple: [Spyridon Samaras, composed, Flora mirabilis]
-
A.
Flora mirabilis
chosen
Flora mirabilis is an opera by Greek composer Spyridon Samaras, recognized as one of his most important and successful stage works.
-
B.
Flora
Flora is a celebrated 19th-century botanical illustration by Mary Evelyn Pickering that showcases her detailed and artistic rendering of plant life.
-
C.
Flora
Flora is a symbolist painting by Evelyn De Morgan depicting the Roman goddess of flowers and spring in a richly allegorical, Pre-Raphaelite-inspired style.
-
D.
Flora
Flora is the middle name of Ruth Disney, the daughter of Walt Disney and his wife Lillian.
-
E.
Flora
Flora is one of the three good fairies in Disney's "Sleeping Beauty," known for her red attire, leadership among the fairies, and role in protecting Princess Aurora.
- 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_69d8dd04f4488190b1121cc53ef2bfd6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e19ea01c8190b9bb789da32f9a90 |
completed | April 20, 2026, 8:19 a.m. |
Created at: April 10, 2026, 12:04 p.m.