Triple
T34672283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Decimation |
E890406
|
entity |
| Predicate | effectOnEarth |
P139733
|
FINISHED |
| Object | loss of approximately half of Earth’s population |
—
|
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: loss of approximately half of Earth’s population | Statement: [The Decimation, effectOnEarth, loss of approximately half of Earth’s population]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOnEarth Context triple: [The Decimation, effectOnEarth, loss of approximately half of Earth’s population]
-
A.
riskToEarth
Indicates that something poses a potential threat, danger, or harmful impact to Earth.
-
B.
effectOnWorld
chosen
Indicates how an entity’s actions or existence change, influence, or impact the state of the world.
-
C.
earth
Indicates that an entity is the planet Earth or is located on, associated with, or pertaining to Earth.
-
D.
forEarthApprox
Indicates an approximate or estimated value or condition as it pertains to Earth or an Earth-related context.
-
E.
effectOnOcean
Indicates the impact or influence that something has on the state, conditions, or processes of the ocean.
- 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_69f349d9c59481908b36baa0be093aea |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fd4129a8848190a5002150278ac689 |
completed | May 8, 2026, 1:49 a.m. |
| PD | Predicate disambiguation | batch_69fd3e0515ec8190937c7af71ebc3875 |
completed | May 8, 2026, 1:36 a.m. |
Created at: May 1, 2026, 2:05 a.m.