Triple
T12218965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rakaia River |
E291159
|
entity |
| Predicate | Rakaia GorgeLocatedIn |
P30683
|
FINISHED |
| Object | foothills of the Southern Alps |
—
|
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: foothills of the Southern Alps | Statement: [Rakaia River, Rakaia GorgeLocatedIn, foothills of the Southern Alps]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Rakaia GorgeLocatedIn Context triple: [Rakaia River, Rakaia GorgeLocatedIn, foothills of the Southern Alps]
-
A.
notableGorge
Indicates a relationship where a gorge is recognized as notable, significant, or of particular interest in some context.
-
B.
gorgeName
Indicates that an entity has or is identified by the name of a gorge.
-
C.
hasRaftingDifficulty
Indicates that an entity is associated with a specific level of rafting difficulty.
-
D.
refersToNaturalWonder
Indicates that one entity makes reference to, mentions, or points specifically to a natural wonder (such as a notable natural landmark or formation).
-
E.
locatedInGeographicFeature
chosen
Indicates that something is situated within or on a specific natural geographic feature (such as a mountain, river, valley, or lake).
- 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_69d6ab65923081909acfc61b7a612233 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d920e312708190b4aede2e21f5f697 |
completed | April 10, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69d91c3d669c81908eea7ad61122d275 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.