Triple
T13468687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Manitou |
E311572
|
entity |
| Predicate | isOnIslandInLake |
P110495
|
FINISHED |
| Object | Manitoulin Island on Lake Huron |
—
|
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: Manitoulin Island on Lake Huron | Statement: [Lake Manitou, isOnIslandInLake, Manitoulin Island on Lake Huron]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOnIslandInLake Context triple: [Lake Manitou, isOnIslandInLake, Manitoulin Island on Lake Huron]
-
A.
isInLake
Indicates that one entity is located within the body of water defined as a lake.
-
B.
isOnSideOfIsland
Indicates that one entity is located on a particular side or shore of an island relative to some reference or division.
-
C.
isInIsland
Indicates that one entity is located within the geographic boundaries of an island.
-
D.
isInlandWaterBodyOf
Indicates that one water body is an inland (non-oceanic) water feature that is geographically part of, contained within, or associated with another entity.
-
E.
isIsland
Indicates that the subject entity is classified as an island, i.e., a landmass surrounded by water.
- F. None of above. chosen
Provenance (4 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_69d806a938b8819097ec43a2229fc7f9 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf21e46081908a00c9acf54f270f |
completed | April 12, 2026, 2:41 p.m. |
| PD | Predicate disambiguation | batch_69dbadfddefc81909ef7fde23b181b5c |
completed | April 12, 2026, 2:36 p.m. |
| PDg | Predicate description generation | batch_69dbaecc98cc8190829f5be759c4f1e3 |
completed | April 12, 2026, 2:40 p.m. |
Created at: April 9, 2026, 9:42 p.m.