Triple
T7864973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Himadri |
E182592
|
entity |
| Predicate | hasPeak |
P8205
|
FINISHED |
| Object | Shishapangma |
E221528
|
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: Shishapangma | Statement: [Himadri, hasPeak, Shishapangma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shishapangma Context triple: [Himadri, hasPeak, Shishapangma]
-
A.
Shishapangma
chosen
Shishapangma is one of the world’s fourteen eight-thousanders, a major Himalayan peak located entirely within Tibet, China.
-
B.
Gyachung Kang
Gyachung Kang is a prominent Himalayan mountain peak, one of the world’s highest, located between Nepal and China in the Mahalangur Himal range.
-
C.
Shkhara
Shkhara is a prominent peak in the Greater Caucasus mountain range, known as one of the highest and most challenging mountains in the region.
-
D.
Ama Dablam
Ama Dablam is a striking, pyramid-shaped mountain in the Himalayas of eastern Nepal, renowned among climbers for its technical routes and dramatic prominence near Mount Everest.
-
E.
Makalu
Makalu is the fifth-highest mountain in the world, a prominent 8,485-meter peak on the border between Nepal and China known for its steep faces and challenging climbing routes.
- 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_69ca82894d9081908a832bfce71a4714 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb36c0eaa48190a0df4c37c726546e |
completed | March 31, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfb9e1afb08190a1befb047ee96ca8 |
completed | April 3, 2026, 1 p.m. |
Created at: March 30, 2026, 4:54 p.m.