Triple
T17879080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | little spotted kiwi |
E447031
|
entity |
| Predicate | isRarestKiwiSpecies |
P37663
|
FINISHED |
| Object | one of the rarest kiwi species |
—
|
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: one of the rarest kiwi species | Statement: [little spotted kiwi, isRarestKiwiSpecies, one of the rarest kiwi species]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isRarestKiwiSpecies Context triple: [little spotted kiwi, isRarestKiwiSpecies, one of the rarest kiwi species]
-
A.
isRareTypeOf
chosen
Indicates that one entity is an uncommon or infrequently occurring subtype or category of another entity.
-
B.
isCherrySpecies
Indicates that one entity is a biological species classified as a type of cherry in relation to another entity.
-
C.
isInlandVarietyOf
Indicates that one entity is a variety or subtype of another that occurs specifically in inland (non-coastal) areas.
-
D.
isOneOfLargestPlantsOf
Indicates that the subject is among the largest plants within the group or category specified by the object.
-
E.
hasLargestSpecies
Indicates that one entity possesses, contains, or is associated with the species that is largest in size or extent within a given group or context.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49c0d219481909830fc269fc6beb5 |
completed | April 19, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69e3d8e6d2e88190ad9ef9f8a99f13e6 |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:18 a.m.