Triple
T17299765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | America’s Cup |
E420009
|
entity |
| Predicate | notableClassOfBoat |
P88354
|
FINISHED |
| Object | AC72 |
E420014
|
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: AC72 | Statement: [America’s Cup, notableClassOfBoat, AC72]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AC72 Context triple: [America’s Cup, notableClassOfBoat, AC72]
-
A.
AC72 catamaran
chosen
The AC72 catamaran is a high-performance, wing-sailed racing yacht class designed for extreme speed and used in the America's Cup.
-
B.
Jetstream 41
The Jetstream 41 is a small twin-turboprop regional airliner designed for short-haul commuter routes, originally developed by British Aerospace in the early 1990s.
-
C.
America’s Cup Class
America’s Cup Class is a high-performance yacht design rule used to create the cutting-edge racing boats that compete in the prestigious America’s Cup sailing competition.
-
D.
Nautica
Nautica is an American lifestyle brand best known for its nautical-inspired apparel and accessories.
-
E.
FJ dinghy
The FJ dinghy is a popular two-person sailing dinghy widely used for collegiate and club racing and training.
- 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e438f9e5ac8190ba0b5820790112d9 |
completed | April 19, 2026, 2:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0180da5b808190857c51aaa2e85339 |
completed | May 11, 2026, 7:10 a.m. |
Created at: April 10, 2026, 5:41 a.m.