Triple
T14669074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sully Erna |
E344458
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Salvatore |
E393786
|
NE FINISHED |
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: Salvatore | Statement: [Sully Erna, givenName, Salvatore]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salvatore Context triple: [Sully Erna, givenName, Salvatore]
-
A.
Salvatore
chosen
Salvatore is the given name of Salvador Luria, the Nobel Prize–winning Italian-American microbiologist and pioneer of bacterial genetics.
-
B.
Vito
Vito is a masculine given name of Italian origin, famously borne by mob boss Vito Genovese and the fictional character Vito Corleone.
-
C.
Gennaro
Gennaro is the surname of Angie Gennaro, a fictional character from Dennis Lehane’s crime novels.
-
D.
Gennaro
Gennaro is an Italian masculine given name, traditionally common in southern Italy and associated with Saint Januarius, the patron saint of Naples.
-
E.
Salvatore Naturale
Salvatore Naturale is a fictional bank robber character from the film "Dog Day Afternoon," known for being the nervous and volatile partner in the movie’s botched heist.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d822e283fc8190a0e4c235cf880052 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb54dda1c8190bf16d17e26a2bba6 |
completed | April 14, 2026, 9:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdd5e9bb2081908515ab6430e9b1c2 |
completed | May 8, 2026, 12:24 p.m. |
Created at: April 10, 2026, 1:27 a.m.