Triple
T9573939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Speedskating |
E230994
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | USS |
E123727
|
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: USS | Statement: [U.S. Speedskating, abbreviation, USS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: USS Context triple: [U.S. Speedskating, abbreviation, USS]
-
A.
USS
chosen
USS is the standard ship prefix used by the United States Navy to denote a commissioned vessel of the U.S. fleet.
-
B.
USS Archerfish
USS Archerfish was a U.S. Navy Balao-class submarine in World War II, best known for sinking the Japanese aircraft carrier Shinano in 1944.
-
C.
USS Reliant
The USS Reliant is a Miranda-class Federation starship best known as the vessel commandeered by Khan Noonien Singh in the film "Star Trek II: The Wrath of Khan."
-
D.
USS Cassin Young
USS Cassin Young is a preserved World War II-era Fletcher-class destroyer now serving as a museum ship in Boston, Massachusetts.
-
E.
USS Ticonderoga
USS Ticonderoga was a U.S. Navy aircraft carrier that notably served as a recovery ship for several NASA missions, including Apollo 17.
- 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_69ca848091c48190bc313d6620d09555 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd99a94c788190a4bb5d2b676908ac |
completed | April 1, 2026, 10:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d152bf5c548190b6c33cc49e418ef7 |
completed | April 4, 2026, 6:04 p.m. |
Created at: March 30, 2026, 8:05 p.m.