Triple
T18209657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lightship Huron |
E435996
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Lightship Huron |
—
|
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: Lightship Huron | Statement: [Lightship Huron, name, Lightship Huron]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lightship Huron Context triple: [Lightship Huron, name, Lightship Huron]
-
A.
Lightship Huron
chosen
Lightship Huron is a historic Great Lakes lightship now preserved as a museum vessel in Port Huron, Michigan.
-
B.
Trudy Ship
Trudy Ship is a film editor best known for her work on the drama "Mr. Holland's Opus."
-
C.
Lightship Chesapeake
Lightship Chesapeake is a historic U.S. lightship that once served as a floating lighthouse and is now preserved as a museum ship in Baltimore.
-
D.
M/V LeConte
M/V LeConte is an Alaska Marine Highway System ferry that provides passenger and vehicle service to coastal communities in Southeast Alaska.
-
E.
HMS Margaretta
HMS Margaretta was a British armed schooner notable for being captured by American colonists during the 1775 Battle of Machias, one of the first naval engagements of the American Revolutionary War.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e2276d7c8190883fa3f6f7b81133 |
completed | April 19, 2026, 2:09 p.m. |
Created at: April 10, 2026, 10:32 a.m.