Triple
T21337596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antonio Scarpacci |
E526090
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Sandpiper Air |
—
|
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: Sandpiper Air | Statement: [Antonio Scarpacci, associatedWith, Sandpiper Air]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandpiper Air Context triple: [Antonio Scarpacci, associatedWith, Sandpiper Air]
-
A.
Sandpiper Air
chosen
Sandpiper Air is the small Nantucket-based commuter airline featured in the American sitcom "Wings."
-
B.
Princeville Airways
Princeville Airways was a regional Hawaiian airline that operated inter-island flights before rebranding as Island Air.
-
C.
Sunrise Airways
Sunrise Airways is a Haitian airline that operates regional passenger flights throughout the Caribbean, with its main base in Port-au-Prince.
-
D.
Northern Air
Northern Air is a regional airline based in Fiji that operates domestic flights connecting smaller islands and remote communities.
-
E.
Air Taxi Co.
Air Taxi Co. was the original company that evolved into Iran Aseman Airlines, an Iranian air carrier.
- 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_69e0b51c33048190ab27cede74ef798c |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e898da015081909e83fb62cf166b9a |
completed | April 22, 2026, 9:46 a.m. |
Created at: April 16, 2026, 4:43 p.m.