Triple
T22715009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Catald |
E561704
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object | San Cataldo |
—
|
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: San Cataldo | Statement: [Saint Catald, alternativeName, San Cataldo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: San Cataldo Context triple: [Saint Catald, alternativeName, San Cataldo]
-
A.
San Cataldo
chosen
San Cataldo is a town in central Sicily, Italy, known for its agricultural economy and proximity to the provincial capital of Caltanissetta.
-
B.
San Cataldo Church
San Cataldo Church is a historic Catholic church associated with the hilltop town of Erice in Sicily, Italy, known for its medieval architecture and religious significance.
-
C.
Lodi Cathedral
Lodi Cathedral is a historic Roman Catholic church and prominent architectural landmark located in the city of Lodi in northern Italy.
-
D.
Santa Felicita
Santa Felicita is a church in the Italian town of Affile, known as a local place of Catholic worship and community life.
-
E.
Santa Felicita
Santa Felicita is a historic Roman Catholic church in Florence, Italy, noted for its Renaissance art and architecture.
- 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_69e2454f1348819088d83f420925a5c1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1790ca59881909064d49f331fb711 |
completed | April 29, 2026, 3:20 a.m. |
Created at: April 17, 2026, 3:18 p.m.