Triple
T6123083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French Lick Springs Hotel |
E136528
|
entity |
| Predicate | nearbyAttraction |
P3449
|
FINISHED |
| Object | Patoka Lake |
E566852
|
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: Patoka Lake | Statement: [French Lick Springs Hotel, nearbyAttraction, Patoka Lake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patoka Lake Context triple: [French Lick Springs Hotel, nearbyAttraction, Patoka Lake]
-
A.
Patoka Lake
chosen
Patoka Lake is a large reservoir and popular outdoor recreation destination in southern Indiana known for boating, fishing, camping, and wildlife viewing.
-
B.
Conesus Lake
Conesus Lake is one of the smaller western lakes in New York’s Finger Lakes region, known for recreation, cottages, and scenic rural surroundings.
-
C.
Mayfield Lake
Mayfield Lake is a large reservoir in southwestern Washington State popular for boating, fishing, and camping.
-
D.
Wilson Lake
Wilson Lake is a man-made reservoir in northern Alabama known for hydroelectric power generation, navigation, and recreational activities along the Tennessee River.
-
E.
Wilson Lake
Wilson Lake is a scenic freshwater lake in western Maine known for recreation such as boating, fishing, and lakeside camping.
- 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_69c0089f851c81909e5e189a617dcff6 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05c247b7081909972b40afb165e6f |
completed | March 22, 2026, 9:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c243bd199081909a96366cc39bf43e |
completed | March 24, 2026, 7:56 a.m. |
Created at: March 22, 2026, 4:14 p.m.