Triple
T7547378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gillson Beach |
E178439
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Wilmette Harbor |
E154273
|
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: Wilmette Harbor | Statement: [Gillson Beach, near, Wilmette Harbor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wilmette Harbor Context triple: [Gillson Beach, near, Wilmette Harbor]
-
A.
Wilmette Harbor
chosen
Wilmette Harbor is a small recreational marina on Lake Michigan known for boating, sailing, and access to the nearby Baha'i House of Worship in Wilmette, Illinois.
-
B.
Lincoln Harbor
Lincoln Harbor is a mixed-use waterfront area along the Hudson River in Weehawken, New Jersey, featuring residential buildings, offices, a marina, and transit connections to Manhattan.
-
C.
Seeadler Harbor
Seeadler Harbor is a large natural harbor in the Admiralty Islands that served as a major Allied naval base and logistics hub in the Pacific during World War II.
-
D.
Waukegan Harbor
Waukegan Harbor is a commercial and recreational port facility on Lake Michigan serving the city of Waukegan, Illinois.
-
E.
Milwaukee Harbor
Milwaukee Harbor is a commercial and recreational port area on Lake Michigan serving the city of Milwaukee, Wisconsin.
- 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_69c69f2cbe08819088f9eb0c03ef529b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f89a7b2c8190b2ca57edbb4f0390 |
completed | March 27, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c84f2662f881909f65c936be9eab56 |
completed | March 28, 2026, 9:59 p.m. |
Created at: March 27, 2026, 3:49 p.m.