Triple
T11583463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Interlochen |
E274688
|
entity |
| Predicate | hasNearbyWaterBody |
P1489
|
FINISHED |
| Object | Green Lake |
E1101851
|
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: Green Lake | Statement: [Interlochen, hasNearbyWaterBody, Green Lake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Green Lake Context triple: [Interlochen, hasNearbyWaterBody, Green Lake]
-
A.
Green Lake
chosen
Green Lake is a freshwater lake in northwestern Michigan known for its clear waters, recreational activities, and proximity to the arts-focused community of Interlochen.
-
B.
North Lake
North Lake is a scenic alpine lake in California’s Eastern Sierra Nevada, popular for fishing, hiking, and as a gateway to high-country trails near Bishop.
-
C.
North Lake
North Lake is a scenic body of water in New York’s Catskill Mountains popular for camping, hiking, fishing, and boating.
-
D.
Green Lake, Wisconsin
Green Lake, Wisconsin is a small resort city in central Wisconsin known for its deep, spring-fed lake, outdoor recreation, and tourism.
-
E.
Lake Monona
Lake Monona is a prominent freshwater lake in Madison, Wisconsin, known for its recreational activities, scenic shoreline, and views of the city’s skyline and state capitol.
- 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_69d6aae6b14c81908dc5a74bad7591f9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8904db5748190ae5f10ae86ccdf46 |
completed | April 10, 2026, 5:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd7a2796cc81908b6d4cf71f39e88a |
completed | May 8, 2026, 5:52 a.m. |
Created at: April 8, 2026, 9:38 p.m.