Triple
T4871282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kedarnath Temple |
E109089
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Mandakini River |
E529240
|
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: Mandakini River | Statement: [Kedarnath Temple, near, Mandakini River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mandakini River Context triple: [Kedarnath Temple, near, Mandakini River]
-
A.
Mandakini River
chosen
The Mandakini River is a Himalayan river in Uttarakhand, India, revered in Hinduism and known for flowing past the Kedarnath temple before joining the Alaknanda River.
-
B.
Parbati River
The Parbati River is a Himalayan river in northern India that flows through the Parvati Valley of Himachal Pradesh before joining the Beas River.
-
C.
Parbati River
The Parbati River is a significant river in central India that contributes to the Chambal River system and supports agriculture and local ecosystems along its course.
-
D.
Gambhir River
The Gambhir River is a river in northwestern India that helps sustain the wetlands and rich birdlife of Keoladeo National Park in Rajasthan.
-
E.
Ramganga River
The Ramganga River is a major tributary of the Ganges in northern India, flowing through the state of Uttar Pradesh and supporting cities like Bareilly along its course.
- 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_69bd440d96a48190b0c87069adef2af1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d9c77b88190b3e6884c9752ebbb |
completed | March 20, 2026, 3:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c761601814819092889a7d6ba74a02 |
completed | March 28, 2026, 5:04 a.m. |
Created at: March 20, 2026, 1:27 p.m.