Triple
T36541866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Little Barrier Island Nature Reserve |
E901042
|
entity |
| Predicate | notableSpeciesConserved |
P68322
|
FINISHED |
| Object | kōkako |
E168379
|
NE 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: kōkako | Statement: [Little Barrier Island Nature Reserve, notableSpeciesConserved, kōkako]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableSpeciesConserved Context triple: [Little Barrier Island Nature Reserve, notableSpeciesConserved, kōkako]
-
A.
notableSpecies
Indicates that the subject is known for, or significantly associated with, the specified species.
-
B.
conservationFocusSpecies
chosen
Indicates that a conservation effort, program, or context is specifically directed toward or centered on a particular species.
-
C.
notableSpeciesGroup
Indicates that an entity is a significant or characteristic member of a particular species group associated with another entity.
-
D.
notableSpeciesRole
Indicates that a species plays a particularly important, characteristic, or influential role in relation to another entity or context.
-
E.
habitatOfNotableSpecies
Indicates that a location serves as the natural environment or living area for one or more notable species.
- F. None of above.
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_69f76e61217081908b79d610fe67b013 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39e6e168948190aca0fe37ad65695c |
completed | June 23, 2026, 1:52 a.m. |
| PD | Predicate disambiguation | batch_6a037a0bf4b88190bdcfae9a14b51f0a |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:11 p.m.