Triple
T5173508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rottnest Island |
E116739
|
entity |
| Predicate | hasBeach |
P1922
|
FINISHED |
| Object |
Parker Point
Parker Point is a popular scenic beach and snorkeling spot on Rottnest Island off the coast of Western Australia.
|
E499421
|
NE FINISHED |
How this triple was built (4 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: Parker Point | Statement: [Rottnest Island, hasBeach, Parker Point]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Parker Point Context triple: [Rottnest Island, hasBeach, Parker Point]
-
A.
Brown’s Point
Brown’s Point is a coastal neighborhood and headland in Tacoma, Washington, known for its historic lighthouse and views over Commencement Bay and Puget Sound.
-
B.
Greenleaf Point
Greenleaf Point is a prominent geographic area in Washington, D.C., situated at the confluence of the Anacostia and Potomac Rivers.
-
C.
Terrapin Point
Terrapin Point is a popular scenic overlook on the U.S. side of Niagara Falls offering close-up views of the Horseshoe Falls.
-
D.
Sandy Point
Sandy Point is a small coastal settlement on the island of North Caicos in the Turks and Caicos Islands, known for its quiet beaches and laid-back atmosphere.
-
E.
Roches Point
Roches Point is a small lakeside community within the town of Georgina in Ontario, Canada, known for its location on the shores of Lake Simcoe.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Parker Point Triple: [Rottnest Island, hasBeach, Parker Point]
Generated description
Parker Point is a popular scenic beach and snorkeling spot on Rottnest Island off the coast of Western Australia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Parker Point Target entity description: Parker Point is a popular scenic beach and snorkeling spot on Rottnest Island off the coast of Western Australia.
-
A.
Brown’s Point
Brown’s Point is a coastal neighborhood and headland in Tacoma, Washington, known for its historic lighthouse and views over Commencement Bay and Puget Sound.
-
B.
Greenleaf Point
Greenleaf Point is a prominent geographic area in Washington, D.C., situated at the confluence of the Anacostia and Potomac Rivers.
-
C.
Terrapin Point
Terrapin Point is a popular scenic overlook on the U.S. side of Niagara Falls offering close-up views of the Horseshoe Falls.
-
D.
Sandy Point
Sandy Point is a small coastal settlement on the island of North Caicos in the Turks and Caicos Islands, known for its quiet beaches and laid-back atmosphere.
-
E.
Roches Point
Roches Point is a small lakeside community within the town of Georgina in Ontario, Canada, known for its location on the shores of Lake Simcoe.
- F. None of above. chosen
Provenance (5 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_69bd445ff97c81909a2615cc56235470 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd796f7c308190a721e33aabd499ac |
completed | March 20, 2026, 4:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bed9471b4881909c8436853818a8a0 |
completed | March 21, 2026, 5:45 p.m. |
| NEDg | Description generation | batch_69bed9f3624c8190b9d22fa0594dd767 |
completed | March 21, 2026, 5:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69beda5d39b88190a7314f673de2719d |
completed | March 21, 2026, 5:50 p.m. |
Created at: March 20, 2026, 1:45 p.m.