Triple
T25609898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018 Amesbury poisoning |
E642017
|
entity |
| Predicate | timeAfterRelatedEvent |
P54905
|
FINISHED |
| Object | several months after 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: several months after Salisbury attack | Statement: [2018 Amesbury poisoning, timeAfterRelatedEvent, several months after Salisbury attack]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeAfterRelatedEvent Context triple: [2018 Amesbury poisoning, timeAfterRelatedEvent, several months after Salisbury attack]
-
A.
timePeriodAfter
Indicates that one time period occurs entirely later than another time period in a temporal sequence.
-
B.
timeAfterAble
Indicates that one event, state, or action occurs after another point in time at which it becomes possible or permissible.
-
C.
timeCorrelation
Indicates that two events or states are related in time such that changes or occurrences in one are systematically associated with changes or occurrences in the other.
-
D.
laterRelatedEvent
chosen
Indicates that one event is temporally related to another by occurring at a later time.
-
E.
timePeriodEvent
Indicates that an event occurs, is scheduled, or is valid within a specified time period.
- 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.