Triple
T10130140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Johns |
E226315
|
entity |
| Predicate | hasPark |
P105
|
FINISHED |
| Object | Pier Park |
E201929
|
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: Pier Park | Statement: [St. Johns, hasPark, Pier Park]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pier Park Context triple: [St. Johns, hasPark, Pier Park]
-
A.
Pier Park
Pier Park is a large outdoor shopping, dining, and entertainment complex that serves as a central tourist hub in Panama City Beach, Florida.
-
B.
Pier Park
chosen
Pier Park is a large wooded public park in North Portland known for its forested trails, disc golf course, and recreational facilities.
-
C.
Pier Park
Pier Park is a waterfront recreational park in Grosse Pointe Farms, Michigan, offering residents access to Lake St. Clair with amenities such as a beach, marina, and picnic areas.
-
D.
Pier C Park
Pier C Park is a modern waterfront recreational park on the Hudson River in Hoboken, New Jersey, known for its playgrounds, lawns, and views of the Manhattan skyline.
-
E.
Pier A Park
Pier A Park is a popular waterfront green space in Hoboken, New Jersey, known for its Manhattan skyline views, open lawns, and recreational areas along the Hudson River.
- 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_69ca843057b48190a86730167f5d6b98 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd33438988190be45878f98695816 |
completed | April 2, 2026, 2:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2e5ce3fcc8190b1d07dbba34d6bff |
completed | April 5, 2026, 10:44 p.m. |
Created at: March 30, 2026, 9:05 p.m.