Triple
T22680328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mont Panié |
E560461
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Hienghène |
—
|
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: Hienghène | Statement: [Mont Panié, near, Hienghène]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hienghène Context triple: [Mont Panié, near, Hienghène]
-
A.
Hienghène
chosen
Hienghène is a coastal commune in the North Province of New Caledonia, known for its dramatic limestone rock formations and cultural significance to the indigenous Kanak people.
-
B.
Hingna
Hingna is a town in the Nagpur metropolitan region of Maharashtra, India, known for its industrial areas and proximity to Nagpur city.
-
C.
Hunsingore
Hunsingore is a small village in North Yorkshire, England, known historically as the burial place of astronomer John Goodricke.
-
D.
Banyara
The Banyara are an ethnic group indigenous to eastern Uganda, known for their distinct cultural traditions and local agricultural livelihoods.
-
E.
Hauya
Hauya is a small genus of flowering plants in the evening primrose family, native to mountainous regions of Central and South America.
- 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_69e2454bfd00819099115715a22cb057 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1785f68b4819082c5570f741f5135 |
completed | April 29, 2026, 3:17 a.m. |
Created at: April 17, 2026, 3:11 p.m.