Triple
T9941500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saco Bay |
E194092
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object | Stage Island |
E787621
|
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: Stage Island | Statement: [Saco Bay, hasIsland, Stage Island]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stage Island Context triple: [Saco Bay, hasIsland, Stage Island]
-
A.
Stage Island
chosen
Stage Island is a small coastal island located near the village of Cape Porpoise in the town of Kennebunkport, Maine.
-
B.
Sea Island
Sea Island is a small island in Richmond, British Columbia, best known as the site of Vancouver International Airport and associated aviation and commercial facilities.
-
C.
Sea Island
Sea Island is an exclusive resort and residential community on the Georgia coast, renowned for its luxury accommodations, golf courses, and seaside amenities.
-
D.
Border Island
Border Island is a small, scenic island within Australia’s Whitsunday Islands renowned for its fringing coral reefs, clear waters, and protected marine and birdlife.
-
E.
Anchor Island
Anchor Island is an island located within Dusky Sound, a remote and rugged fiord in Fiordland, southwestern New Zealand.
- 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_69ca82e409348190a393777356b80a2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb610905c81909d669265c92021a5 |
completed | April 2, 2026, 12:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d229080d0081908b66b9c4166db252 |
completed | April 5, 2026, 9:19 a.m. |
Created at: March 30, 2026, 8:44 p.m.