Triple
T25908044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Sealy |
E652808
|
entity |
| Predicate | onLandmass |
P159560
|
FINISHED |
| Object | South Island of New Zealand |
—
|
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: South Island of New Zealand | Statement: [Mount Sealy, onLandmass, South Island of New Zealand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onLandmass Context triple: [Mount Sealy, onLandmass, South Island of New Zealand]
-
A.
majorLandmasses
Indicates that the related entities are the primary, large continuous expanses of land on a planetary surface.
-
B.
isLandOf
Indicates that a specified area or territory belongs to, is governed by, or is characteristically associated with a particular entity (such as a country, people, or ruler).
-
C.
nearestLandmass
Indicates that one landmass is the closest geographically to another specified point or landmass.
-
D.
isLargestContiguousLandmass
Indicates that one landmass is the largest single, unbroken continuous area of land compared to all other landmasses in the relevant context.
-
E.
hasLargestContinuousLandAreaOn
Indicates that an entity possesses the greatest uninterrupted expanse of land on a specified geographic region or surface compared to all other entities.
- F. None of above. chosen
Provenance (4 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_69e7ab3d3f8481909bc53ed64c06af33 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f603c15b348190a7f00745b6475b28 |
completed | May 2, 2026, 2:01 p.m. |
| PD | Predicate disambiguation | batch_69f4a0fed15881909b789251fe5d8d45 |
completed | May 1, 2026, 12:47 p.m. |
| PDg | Predicate description generation | batch_69f55e497fa081909bc59a7b92c5df59 |
completed | May 2, 2026, 2:15 a.m. |
Created at: April 22, 2026, 8:27 a.m.