Triple
T13591127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iruppu Falls |
E324693
|
entity |
| Predicate | accessByRoadFrom |
P22549
|
FINISHED |
| Object | Madikeri |
E324694
|
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: Madikeri | Statement: [Iruppu Falls, accessByRoadFrom, Madikeri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Madikeri Context triple: [Iruppu Falls, accessByRoadFrom, Madikeri]
-
A.
Madikeri
chosen
Madikeri is a scenic hill town in Karnataka’s Coorg region, known for its cool climate, coffee plantations, and lush Western Ghats landscapes.
-
B.
Sullia
Sullia is a town in the Dakshina Kannada district of Karnataka, India, known as a local commercial and educational center in the region.
-
C.
Mysuru
Mysuru is a historic city in the southern Indian state of Karnataka, renowned for its royal heritage, palaces, and cultural festivals such as Dasara.
-
D.
Mangalore
Mangalore is a major port city on the southwestern coast of India, known for its maritime trade, diverse culture, and role as a commercial hub of Karnataka.
-
E.
Gadag
Gadag is a historic town in Karnataka, India, renowned for its richly carved medieval temples and monuments from the Western Chalukya architectural tradition.
- 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_69d80769eaf081909d82f44e484d6113 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb056ce088190a6feb4266633d18b |
completed | April 12, 2026, 2:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd9498f8848190a170a3d41c9e3a76 |
completed | May 8, 2026, 7:45 a.m. |
Created at: April 9, 2026, 9:49 p.m.