Triple
T21571097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Nimba |
E532283
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Mont Nimba |
—
|
NE NERFINISHED |
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: Mont Nimba | Statement: [Mount Nimba, alsoKnownAs, Mont Nimba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mont Nimba Context triple: [Mount Nimba, alsoKnownAs, Mont Nimba]
-
A.
Mount Nimba
chosen
Mount Nimba is a prominent West African mountain massif known for its rich biodiversity and UNESCO World Heritage–listed nature reserve spanning Guinea, Liberia, and Côte d’Ivoire.
-
B.
Buea Mountain
Buea Mountain, also known as Mount Cameroon, is an active volcano and the highest peak in West and Central Africa, located near the town of Buea in Cameroon.
-
C.
Guinean Loma
Guinean Loma is a regional variety of the Loma language spoken primarily in parts of Guinea.
-
D.
Mount Afadja
Mount Afadja is one of Ghana’s highest and most popular mountains, renowned for its scenic hiking trails and panoramic views near the border with Togo.
-
E.
Monte Cinto
Monte Cinto is the tallest mountain in Corsica, renowned for its rugged alpine terrain and panoramic views over the island and the Mediterranean Sea.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c460db088190828c64206a450273 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eee9cc5c448190887a836f577d01ba |
completed | April 27, 2026, 4:45 a.m. |
Created at: April 16, 2026, 6:30 p.m.