Triple
T21492114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaikōura Canyon |
E530262
|
entity |
| Predicate | extendsToDepth |
P1673
|
FINISHED |
| Object | more than 1000 m below sea level |
—
|
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: more than 1000 m below sea level | Statement: [Kaikōura Canyon, extendsToDepth, more than 1000 m below sea level]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: extendsToDepth Context triple: [Kaikōura Canyon, extendsToDepth, more than 1000 m below sea level]
-
A.
extendsTo
chosen
Indicates that one entity reaches, stretches, or continues its scope, influence, or coverage up to or into another entity.
-
B.
hasDepth
Indicates that an entity possesses a measurable extent or distance from its surface inward or from top to bottom.
-
C.
reachedDepth
Indicates that an entity has arrived at or attained a specified depth level in some medium or context.
-
D.
isDeeperThan
Indicates that one entity has a greater depth or is positioned further down than another entity.
-
E.
hasMaximumDepth
Indicates that an entity possesses a greatest or limiting depth value beyond which it does not extend.
- 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_69e0c45bd15481909fba5910765cdda2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea3ba2fc81909638bbb3e1d92ea5 |
completed | April 23, 2026, 9:45 a.m. |
| PD | Predicate disambiguation | batch_69e631f6e68081908f5ee4ce7413803e |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:23 p.m.