Triple
T22955286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alessandro Ludovisi |
E570738
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Ludovisi |
—
|
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: Ludovisi | Statement: [Alessandro Ludovisi, familyName, Ludovisi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ludovisi Context triple: [Alessandro Ludovisi, familyName, Ludovisi]
-
A.
Canova
Canova was a renowned Italian Neoclassical sculptor celebrated for his marble masterpieces depicting mythological and historical subjects.
-
B.
Donnalucata
Donnalucata is a seaside village in southern Sicily, Italy, known for its sandy beaches, fishing tradition, and role as a holiday destination on the Mediterranean coast.
-
C.
Cantalupani
Cantalupani are the inhabitants of Cantalupo in Sabina, a town in the Lazio region of central Italy.
-
D.
Borghese
chosen
Borghese is an influential Italian noble family historically prominent in Roman politics, the Catholic Church, and art patronage.
-
E.
Viterelli
Viterelli is an Italian surname most notably associated with Joe Viterelli, an American character actor known for his mobster roles in films like "Analyze This."
- 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_69e245b212a88190b5259caf51606084 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f181f09de48190b55913570c965412 |
completed | April 29, 2026, 3:58 a.m. |
Created at: April 17, 2026, 3:47 p.m.