Triple
T466699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sydney |
E8462
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | The Rocks |
E8464
|
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: The Rocks | Statement: [Sydney, hasLandmark, The Rocks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Rocks Context triple: [Sydney, hasLandmark, The Rocks]
-
A.
Vaucluse
Vaucluse is a department in southeastern France’s Provence-Alpes-Côte d’Azur region, known for its historic towns, vineyards, and picturesque landscapes including the Luberon and Mont Ventoux.
-
B.
Halletts Point
Halletts Point is a large-scale waterfront residential and mixed-use development on the Astoria peninsula in Queens, New York City.
-
C.
Sydney Cove
chosen
Sydney Cove is the historic harbor inlet on Sydney Harbour where the First Fleet landed in 1788, marking the beginning of European settlement in Australia.
-
D.
Telegraph Hill
Telegraph Hill is a historic San Francisco neighborhood and prominent hill known for its sweeping bay views, steep stairways, and flocks of wild parrots.
-
E.
Bennelong Point
Bennelong Point is a prominent headland on Sydney Harbour that forms the site of the iconic Sydney Opera House.
- 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_69a2e7f3aeb48190a19453e3a043f486 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2efd831088190b6ac6a56b34a8816 |
completed | Feb. 28, 2026, 1:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a462f7c7b0819097c799a7c53b0e5f |
completed | March 1, 2026, 4:01 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.