Triple
T19802867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Romano |
E475729
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Frank Romano |
—
|
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: Frank Romano | Statement: [Frank Romano, name, Frank Romano]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Romano Context triple: [Frank Romano, name, Frank Romano]
-
A.
Frank Romano
chosen
Frank Romano is a music producer and songwriter known for his work on contemporary R&B and pop tracks, including the song "Just a Dream."
-
B.
Frank Romano
Frank Romano is an author best known for writing the book "Just a Dream."
-
C.
John Romano
John Romano is an American screenwriter and producer known for adapting crime and legal thrillers for film and television, including work on "The Lincoln Lawyer."
-
D.
Donald Gennaro
Donald Gennaro is a lawyer representing InGen in the Jurassic Park franchise, known for his ill-fated visit to the dinosaur theme park.
-
E.
Anthony Perrotti
Anthony Perrotti is a former Rutgers University wrestler best known for becoming the program’s first NCAA All-American in over a decade and helping elevate the Scarlet Knights wrestling program to national prominence.
- 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_69d8e51bc4208190a1c57d8c5d1b15e4 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e654257cb4819096fb2aa5d1f7fbb0 |
completed | April 20, 2026, 4:28 p.m. |
Created at: April 10, 2026, 1:49 p.m.