Triple
T4925291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nch’ḵay̓ |
E110561
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Mt Garibaldi |
E20218
|
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: Mt Garibaldi | Statement: [Nch’ḵay̓, alsoKnownAs, Mt Garibaldi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mt Garibaldi Context triple: [Nch’ḵay̓, alsoKnownAs, Mt Garibaldi]
-
A.
Mount Tapochau
Mount Tapochau is the highest peak on the island of Saipan in the Northern Mariana Islands, known for its panoramic views and World War II historical significance.
-
B.
Mount Garibaldi
chosen
Mount Garibaldi is a glaciated stratovolcano in southwestern British Columbia, Canada, known for its prominent peak overlooking the Sea-to-Sky region near Squamish.
-
C.
Mount Hasan
Mount Hasan is a prominent stratovolcano in central Turkey that forms part of the dramatic volcanic landscape of the Cappadocia region.
-
D.
Mount Heha
Mount Heha is the tallest mountain in Burundi, located in the Burundi Highlands near the city of Bujumbura.
-
E.
Mount Werong
Mount Werong is a prominent peak in New South Wales, Australia, known as the loftiest summit within the Blue Mountains region.
- 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_69bd4413f9908190afcff44d7929cc4c |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd7033c430819088e62f14979aa83c |
completed | March 20, 2026, 4:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be9c44e91881909513a679886cbdef |
completed | March 21, 2026, 1:25 p.m. |
Created at: March 20, 2026, 1:30 p.m.