Triple
T2000534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archean Eon |
E43458
|
entity |
| Predicate | biosphere |
P3591
|
FINISHED |
| Object | dominated by prokaryotes |
—
|
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: dominated by prokaryotes | Statement: [Archean Eon, biosphere, dominated by prokaryotes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: biosphere Context triple: [Archean Eon, biosphere, dominated by prokaryotes]
-
A.
hasBiosphere
Indicates that an entity possesses or supports a biosphere, i.e., a region where living organisms and ecological processes exist.
-
B.
biome
Indicates the type of ecological environment or habitat in which an entity naturally exists or is situated.
-
C.
biota
chosen
Indicates the presence or composition of living organisms (flora, fauna, or other life forms) associated with a given entity or environment.
-
D.
partOfEcosystem
Indicates that an entity functions as a component within a larger ecological system, contributing to and affected by its interactions and processes.
-
E.
biogeographicRole
Indicates the ecological or distributional role an entity plays within a particular biogeographic context or region.
- 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_69a88715dbbc8190b2299e29e955d997 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb87f78f0819098e787a5f3e062fd |
completed | March 7, 2026, 5:32 a.m. |
| PD | Predicate disambiguation | batch_69abb79e63c08190982c8b44a557266f |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:37 p.m.