Triple
T21238430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1988 Spitak earthquake |
E523406
|
entity |
| Predicate | ledToPolicyChange |
P134820
|
FINISHED |
| Object | improvements in Soviet disaster response |
—
|
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: improvements in Soviet disaster response | Statement: [1988 Spitak earthquake, ledToPolicyChange, improvements in Soviet disaster response]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ledToPolicyChange Context triple: [1988 Spitak earthquake, ledToPolicyChange, improvements in Soviet disaster response]
-
A.
hasPolicyChange
chosen
Indicates that a change has been made to an existing policy or set of policies affecting the related entities.
-
B.
sawPolicyChange
Indicates that an entity observed, experienced, or became aware of a change in policy affecting it or its context.
-
C.
changePolicy
Indicates that an entity modifies, replaces, or updates an existing policy governing rules, procedures, or behaviors.
-
D.
policyShift
Indicates a change or adjustment in an existing policy, typically reflecting a new direction, priority, or approach.
-
E.
changeReason
Indicates the reason or justification for a modification or change made to an entity or its state.
- 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_69e0b513b89c81908b27147e91368db2 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e73521eb7c8190b1b97b42d0d052c3 |
completed | April 21, 2026, 8:28 a.m. |
| PD | Predicate disambiguation | batch_69e5f60e1a888190ba75e2e900270a4e |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:46 p.m.