Triple
T25609829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2020 Alexei Navalny poisoning |
E642016
|
entity |
| Predicate | substanceUsedAccordingToOPCW |
P41178
|
FINISHED |
| Object | Novichok-type nerve agent |
—
|
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: Novichok-type nerve agent | Statement: [2020 Alexei Navalny poisoning, substanceUsedAccordingToOPCW, Novichok-type nerve agent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: substanceUsedAccordingToOPCW Context triple: [2020 Alexei Navalny poisoning, substanceUsedAccordingToOPCW, Novichok-type nerve agent]
-
A.
usedSubstance
chosen
Indicates that an entity has consumed, applied, or otherwise made use of a particular substance.
-
B.
canUseSubstance
Indicates that an entity is able or permitted to make use of a particular substance.
-
C.
associatedWithSubstance
Indicates that one entity has a relevant connection or involvement with a particular substance, such as use, presence, exposure, or composition.
-
D.
acceptsSubstance
Indicates that an entity receives, takes in, or allows the use of a specified substance.
-
E.
hasAddictiveSubstance
Indicates that an entity contains or involves a substance capable of causing addiction in those who use or consume it.
- 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_69e75dc6ccf081908d49578fd36a76d5 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f9e1f1408190bab690f67f7d3a31 |
completed | May 2, 2026, 1:19 p.m. |
| PD | Predicate disambiguation | batch_69f4a0f7c6008190ae8cee3e71e19b94 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 21, 2026, 4:40 p.m.