Triple
T21357687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gorgonia of Nazianzus |
E526679
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Gorgonia |
—
|
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: Gorgonia | Statement: [Gorgonia of Nazianzus, givenName, Gorgonia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gorgonia Context triple: [Gorgonia of Nazianzus, givenName, Gorgonia]
-
A.
Gorgonia
chosen
Gorgonia was a pious Christian woman of the 4th century, venerated as a saint and known primarily as the devout sister of Gregory of Nazianzus.
-
B.
Coralli
Coralli is an Italian surname most notably associated with Jean Coralli, a 19th-century ballet master and choreographer of the Romantic era.
-
C.
Diadema
Diadema is an industrial and densely populated municipality in the Greater São Paulo metropolitan area of southeastern Brazil.
-
D.
Chalcomedusa
Chalcomedusa is a figure in Greek mythology known as the wife of Laertes and mother of Odysseus in some traditions.
-
E.
Vandellia
Vandellia is a small, parasitic catfish genus from the Amazon basin, infamous for its blood-feeding habits and reports of entering the orifices of larger animals, including humans.
- 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_69e0b51d8a308190b09113b3b3f9bc15 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8afa2d11c81908608851940e4e6d3 |
completed | April 22, 2026, 11:23 a.m. |
Created at: April 16, 2026, 5:07 p.m.