Triple
T14152045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mouille Point |
E350706
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Green Point |
E556555
|
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: Green Point | Statement: [Mouille Point, adjacentTo, Green Point]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Green Point Context triple: [Mouille Point, adjacentTo, Green Point]
-
A.
Green Point
Green Point is a coastal suburb on the Central Coast of New South Wales, Australia, known for its residential areas and proximity to waterways and natural reserves.
-
B.
Green Point
chosen
Green Point is a coastal suburb of Cape Town, South Africa, known for its urban park, stadium, and proximity to the Atlantic Seaboard.
-
C.
Breezy Point
Breezy Point is a residential coastal neighborhood at the western tip of New York City's Rockaway Peninsula, known for its beaches, private community character, and proximity to the Atlantic Ocean.
-
D.
Rokers Point
Rokers Point is a small coastal settlement located on Little Exuma in The Bahamas.
-
E.
Blue Point
Blue Point is a top-class Godolphin-owned Thoroughbred racehorse best known as a multiple Group 1-winning sprinter, including victories at Royal Ascot.
- 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_69d8278775fc8190b0802d22ca2f495d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6124e23481909e5132a40a1d8624 |
completed | April 14, 2026, 3:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcf7ea34408190830263d7f5a88ce9 |
completed | May 7, 2026, 8:36 p.m. |
Created at: April 10, 2026, 12:57 a.m.