Triple
T27371832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Croix Island |
E690344
|
entity |
| Predicate | formerLargestColonyOf |
P113086
|
FINISHED |
| Object | African penguin |
—
|
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: African penguin | Statement: [St Croix Island, formerLargestColonyOf, African penguin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerLargestColonyOf Context triple: [St Croix Island, formerLargestColonyOf, African penguin]
-
A.
formerColonyName
Indicates that one entity is the historical or previous name used for a colony that later changed its political status or designation.
-
B.
isColonialFoundationOf
Indicates that one entity was established as a colony that later developed into or served as the origin of the other entity.
-
C.
foundedAsColonyOf
Indicates that an entity was originally established as a colony under the control or authority of another entity.
-
D.
foundedAsColonyFor
Indicates that one entity was established as a colony specifically for the benefit, use, or purposes of another entity.
-
E.
largestColonyLocation
chosen
Indicates the location where the largest colony associated with a given entity is found.
- 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_69ef51ff826081909e42c8e2bfb97941 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69fd389cb28c819099a77e28d25f258a |
completed | May 8, 2026, 1:13 a.m. |
| PD | Predicate disambiguation | batch_69fd3826d8048190ada79a5868d1d7f3 |
completed | May 8, 2026, 1:11 a.m. |
Created at: April 27, 2026, 12:19 p.m.