Triple
T33479826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pukaki River |
E857439
|
entity |
| Predicate | hasOriginNear |
P187327
|
FINISHED |
| Object | Southern Alps |
—
|
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: Southern Alps | Statement: [Pukaki River, hasOriginNear, Southern Alps]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOriginNear Context triple: [Pukaki River, hasOriginNear, Southern Alps]
-
A.
hasApproximateOrigin
Indicates that an entity originates from a source or location that is known only approximately rather than precisely.
-
B.
hasOriginIn
Indicates that something begins, arises, or is derived from a specified source, place, or cause.
-
C.
indicatesGeographicOriginNear
chosen
Indicates that one entity originates from a geographic location that is close to or in the vicinity of another specified place.
-
D.
hasLikelyOrigin
Indicates that one entity is inferred or believed, with some degree of uncertainty, to be the source or starting point of another entity.
-
E.
hasSettingOfOrigin
Indicates that something originates from, or was initially set in, a particular setting or environment.
- 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_69f3497472508190b300ebd3fd402367 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fe21b0cba48190b56c39e9f1c0eafa |
completed | May 8, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_69fe204576848190aecf204e2adba5dc |
completed | May 8, 2026, 5:41 p.m. |
Created at: May 1, 2026, 1:38 a.m.