Triple
T11758423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goat Island |
E279589
|
entity |
| Predicate | hasAttraction |
P105
|
FINISHED |
| Object | Terrapin Point |
E307385
|
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: Terrapin Point | Statement: [Goat Island, hasAttraction, Terrapin Point]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terrapin Point Context triple: [Goat Island, hasAttraction, Terrapin Point]
-
A.
Terrapin Point
chosen
Terrapin Point is a popular scenic overlook on the U.S. side of Niagara Falls offering close-up views of the Horseshoe Falls.
-
B.
Parker Point
Parker Point is a popular scenic beach and snorkeling spot on Rottnest Island off the coast of Western Australia.
-
C.
Parker Point
Parker Point is a scenic coastal area and prominent shoreline feature in Blue Hill, Maine, known for its waterfront views and access to Blue Hill Bay.
-
D.
Rokers Point
Rokers Point is a small coastal settlement located on Little Exuma in The Bahamas.
-
E.
Lighthouse Point
Lighthouse Point is a lakeside resort and campground complex at Cedar Point in Sandusky, Ohio, featuring cabins, cottages, RV sites, and amenities for amusement park visitors.
- 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_69d6ab01038c819080714901502c84fc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a5220f148190ae60d1941a579ab6 |
completed | April 10, 2026, 7:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f1309f25a88190b0acaf7d9be6ae59 |
completed | April 28, 2026, 10:11 p.m. |
Created at: April 8, 2026, 9:41 p.m.