Triple
T7886705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marpha |
E183120
|
entity |
| Predicate | accessRoute |
P1985
|
FINISHED |
| Object | Jomsom |
E183979
|
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: Jomsom | Statement: [Marpha, accessRoute, Jomsom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jomsom Context triple: [Marpha, accessRoute, Jomsom]
-
A.
Jomsom
chosen
Jomsom is a popular town in Nepal’s Mustang region, known as a trekking hub on the Annapurna Circuit and a gateway to the Kali Gandaki Valley.
-
B.
Phuentsholing
Phuentsholing is a major Bhutanese border town and commercial hub located on the frontier with India, serving as a key gateway into the country.
-
C.
Marpha
Marpha is a picturesque Thakali village in Nepal’s Mustang region, known for its traditional stone houses, apple orchards, and role as a popular stop on the Annapurna Circuit trekking route.
-
D.
Namche Bazaar
Namche Bazaar is a famous Sherpa town in Nepal’s Khumbu region that serves as the main gateway and acclimatization stop for trekkers and climbers heading toward Mount Everest.
-
E.
Punakha
Punakha is a historic town in western Bhutan that served as the country’s former capital and is known for the majestic Punakha Dzong at the meeting of two rivers.
- 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_69ca828af6e48190a06ee7010d8f0e64 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb39d7e6308190b5a554385e83ff0d |
completed | March 31, 2026, 3:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc5625c7a48190956778b949ab6d23 |
completed | March 31, 2026, 11:17 p.m. |
Created at: March 30, 2026, 4:59 p.m.