Triple
T3052416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kakadu National Park |
E60399
|
entity |
| Predicate | numberOfBirdSpecies |
P6211
|
FINISHED |
| Object | over 280 |
—
|
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: over 280 | Statement: [Kakadu National Park, numberOfBirdSpecies, over 280]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfBirdSpecies Context triple: [Kakadu National Park, numberOfBirdSpecies, over 280]
-
A.
numberOfSpecies
chosen
Indicates the count of distinct species associated with a given entity or context.
-
B.
isMostNumerousBirdSpecies
Indicates that the subject bird species has the largest population size compared to all other bird species in the relevant context.
-
C.
hasBirdSpecies
Indicates that there exists a relationship in which a subject possesses, contains, or is associated with a particular bird species.
-
D.
proportionOfAllBirdSpecies
Indicates the fraction or percentage that a given subset of bird species represents out of all known bird species.
-
E.
recognizedSubspeciesCount
Indicates the number of subspecies that are formally recognized for a given species or taxon.
- 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_69ad8578137c81908259dcb27c7d6d7c |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ad9bf3c52c8190bbe8e5cb98c21715 |
completed | March 8, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69ad962195388190856013a2519c2b0f |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:01 p.m.