Triple
T677803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Manitou Island |
E13115
|
entity |
| Predicate | distanceFromShore |
P15760
|
FINISHED |
| Object | approximately 16 miles west of Leland, Michigan |
—
|
LITERAL 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: approximately 16 miles west of Leland, Michigan | Statement: [South Manitou Island, distanceFromShore, approximately 16 miles west of Leland, Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceFromShore Context triple: [South Manitou Island, distanceFromShore, approximately 16 miles west of Leland, Michigan]
-
A.
distanceFromCoast
chosen
Indicates the measured spatial separation between a location and the nearest point on a coastline.
-
B.
distanceFromMainland
Indicates the measured spatial separation between a location and the nearest point on the mainland.
-
C.
distanceToPacificOcean
Indicates the physical distance between a given location or entity and the Pacific Ocean.
-
D.
shoreType
Indicates the kind or classification of a shoreline associated with a body of water or coastal area.
-
E.
nearestSea
Indicates that one location is the closest sea to a given place compared to all other seas.
- F. None of above.
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_69a4933d3bf88190972041cd8cf143b9 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a04c89148190b6330e86697bb37b |
completed | March 1, 2026, 8:23 p.m. |
| PD | Predicate disambiguation | batch_69a49d1bbd0c81909cfbec30bd17bde7 |
completed | March 1, 2026, 8:10 p.m. |
Created at: March 1, 2026, 7:36 p.m.