Triple
T25609880
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018 Amesbury poisoning |
E642017
|
entity |
| Predicate | nerveAgentSameAs |
P6530
|
FINISHED |
| Object | nerve agent used in Salisbury attack |
—
|
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: nerve agent used in Salisbury attack | Statement: [2018 Amesbury poisoning, nerveAgentSameAs, nerve agent used in Salisbury attack]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nerveAgentSameAs Context triple: [2018 Amesbury poisoning, nerveAgentSameAs, nerve agent used in Salisbury attack]
-
A.
samePersonAs
Indicates that two referenced entities are in fact the very same individual, not just similar or related.
-
B.
equivalentTo
chosen
Indicates that two entities represent the same concept, value, or state, and can be treated as interchangeable in the given context.
-
C.
identifiedAsSameObjectAs
Indicates that two referenced entities are recognized or treated as being the very same underlying object or instance.
-
D.
namedForSimilarityTo
Indicates that one entity is given its name because of a perceived resemblance or likeness to another entity.
-
E.
knowsAs
Indicates that one entity recognizes or refers to another entity by a particular name, alias, or identifier.
- 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_69f480789be08190ab252a6de3797200 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 4:40 p.m.