Triple
T28818772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dhaulagiri region |
E727702
|
entity |
| Predicate | dominantMountainMassif |
P157718
|
FINISHED |
| Object | Dhaulagiri massif |
—
|
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: Dhaulagiri massif | Statement: [Dhaulagiri region, dominantMountainMassif, Dhaulagiri massif]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dominantMountainMassif Context triple: [Dhaulagiri region, dominantMountainMassif, Dhaulagiri massif]
-
A.
nearestMountainMassif
Indicates that one mountain massif is the closest in distance to a given reference location or entity compared to all other mountain massifs.
-
B.
dominantLandformOf
chosen
Indicates that one landform is the primary or most characteristic physical feature of a specified geographic area.
-
C.
highestMassifAmong
Indicates that one massif has the greatest height or prominence among a specified set of massifs.
-
D.
hasMainMountain
Indicates that an entity is primarily associated with or characterized by a specific mountain as its main or most significant mountain.
-
E.
prominenceWithinMassif
Indicates the relative height or distinctness of a peak compared to the surrounding terrain within the same massif.
- F. None of above.
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_69f0319d09088190bbf14cdf1987792a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6f8565134819096aac0175f924a9f |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
Created at: April 28, 2026, 6:33 a.m.