Triple
T22512537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Point |
E556555
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Sea Point |
—
|
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: Sea Point | Statement: [Green Point, adjacentTo, Sea Point]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sea Point Context triple: [Green Point, adjacentTo, Sea Point]
-
A.
Sea Point promenade
chosen
Sea Point promenade is a popular oceanfront walkway in Cape Town known for its scenic Atlantic views, recreational spaces, and vibrant outdoor activity.
-
B.
Ocean Point
Ocean Point was the original name of what is now known as East Rockaway station on the Long Island Rail Road in New York.
-
C.
Ocean Point
Ocean Point was the original name of what is now known as Oceanside station, a rail stop in Oceanside, New York.
-
D.
Marin Headlands
Marin Headlands is a scenic coastal area in Marin County, California, known for its dramatic cliffs, historic military sites, and panoramic views of the Golden Gate Bridge and San Francisco Bay.
-
E.
Seapoint
Seapoint is a luxury residential tower development within Emaar Beachfront in Dubai, offering high-end waterfront apartments and premium amenities.
- 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_69e11e555edc81909ca803587dafd747 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15d61a27881909faed490d2b65f39 |
completed | April 29, 2026, 1:22 a.m. |
Created at: April 16, 2026, 8:50 p.m.