Triple
T289518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Galápagos finches |
E5957
|
entity |
| Predicate | exampleOf |
P1259
|
FINISHED |
| Object | speciation in island systems |
—
|
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: speciation in island systems | Statement: [Galápagos finches, exampleOf, speciation in island systems]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exampleOf Context triple: [Galápagos finches, exampleOf, speciation in island systems]
-
A.
hasExample
chosen
Indicates that one entity serves as an instance, illustration, or concrete example of another entity.
-
B.
demonstratedBy
Indicates that something is shown, proven, or made evident through the actions, behavior, or example of a particular entity.
-
C.
demonstratedConcept
Indicates that an entity has shown, illustrated, or made evident a particular concept through example, explanation, or action.
-
D.
themeExamples
Indicates that the related entity serves as an example or illustration of the theme expressed by the subject.
-
E.
usedToExplain
Indicates that one entity serves as an explanation or clarification for another entity.
- 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_69a25946a7ac8190a78871c210213272 |
completed | Feb. 28, 2026, 2:56 a.m. |
| NER | Named-entity recognition | batch_69a25e4df5508190ab75115ac6b3964e |
completed | Feb. 28, 2026, 3:17 a.m. |
| PD | Predicate disambiguation | batch_69a25b7d089081909810442c3d0182f6 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 3:02 a.m.