Triple
T17080671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pripyat |
E414459
|
entity |
| Predicate | radiationLevel |
P125804
|
FINISHED |
| Object | elevated compared to normal background |
—
|
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: elevated compared to normal background | Statement: [Pripyat, radiationLevel, elevated compared to normal background]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: radiationLevel Context triple: [Pripyat, radiationLevel, elevated compared to normal background]
-
A.
usesRadiation
Indicates that an entity employs radiation as a means or component in performing an action, process, or function.
-
B.
hasRadiationField
Indicates that one entity possesses, generates, or is surrounded by a radiation field associated with another entity.
-
C.
isHighlyRadioactive
Indicates that the subject emits ionizing radiation at a very high level relative to typical or safe standards.
-
D.
majorRadiation
Indicates that one entity is the primary or most significant source of radiation affecting another entity.
-
E.
radiatedFrom
Indicates that something (such as energy, particles, or influence) originates at a source and spreads outward from that source.
- F. None of above. chosen
Provenance (4 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbe2fe7c819099ab0586b1a119f6 |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d642f74819098c014135e249b27 |
completed | April 18, 2026, 10:31 a.m. |
| PDg | Predicate description generation | batch_69e3753f93c88190808fec5692f66699 |
completed | April 18, 2026, 12:12 p.m. |
Created at: April 10, 2026, 5:34 a.m.