Triple
T2874747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miami River |
E56849
|
entity |
| Predicate | mouthLocation |
P417
|
FINISHED |
| Object | Downtown Miami |
E14543
|
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: Downtown Miami | Statement: [Miami River, mouthLocation, Downtown Miami]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Downtown Miami Context triple: [Miami River, mouthLocation, Downtown Miami]
-
A.
Downtown Miami
chosen
Downtown Miami is the central business, cultural, and commercial core of Miami, known for its high-rise skyline, waterfront views, and vibrant urban life.
-
B.
Miami Beach
Miami Beach is a coastal resort city in southeastern Florida known for its sandy beaches, Art Deco Historic District, and vibrant nightlife.
-
C.
South Beach
South Beach is a popular Atlantic Ocean beach on Martha’s Vineyard known for its wide sandy shoreline, strong surf, and scenic dunes.
-
D.
South Beach
South Beach is a waterfront neighborhood in San Francisco known for its bayside views, modern residential developments, and proximity to Oracle Park.
-
E.
South Beach
South Beach is a popular sandy shoreline in Aberystwyth, Wales, known for its promenade, seaside attractions, and views over Cardigan Bay.
- 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_69ab4a4ced288190ab6d3e062d10f7f6 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abe004a64481908f1897d9054a7368 |
completed | March 7, 2026, 8:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b08648923c8190bd544177b825a494 |
completed | March 10, 2026, 8:59 p.m. |
Created at: March 6, 2026, 10:03 p.m.