Triple
T5105473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abel Tasman National Park |
E115081
|
entity |
| Predicate | Abel Tasman Coast Track_type |
P61152
|
FINISHED |
| Object | multi-day tramping track |
—
|
LITERAL 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: multi-day tramping track | Statement: [Abel Tasman National Park, Abel Tasman Coast Track_type, multi-day tramping track]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Abel Tasman Coast Track_type Context triple: [Abel Tasman National Park, Abel Tasman Coast Track_type, multi-day tramping track]
-
A.
trailName
Indicates the name assigned to a specific trail or path in the relationship.
-
B.
extendsAlongCoastOf
Indicates that one entity stretches or runs parallel along the coastline of another entity.
-
C.
trailblazerFor
Indicates that one entity serves as a pioneering example, opening the way or setting a precedent for another entity to follow or build upon.
-
D.
coastName
Indicates that an entity is identified by the name of a specific coast or coastal region.
-
E.
coastOff
Indicates that one entity is located just off the coast of another, typically in nearby offshore waters rather than directly on the shoreline.
- 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_69bd4440b3348190be1251fd8b7951f1 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7589e40c8190a46e4a1b7142be14 |
completed | March 20, 2026, 4:27 p.m. |
| PD | Predicate disambiguation | batch_69bd715e06808190931934dc9930f997 |
completed | March 20, 2026, 4:10 p.m. |
| PDg | Predicate description generation | batch_69bd738ac2e0819099c06cdcc5e21d28 |
completed | March 20, 2026, 4:19 p.m. |
Created at: March 20, 2026, 1:41 p.m.