Triple
T23573941
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1783 Calabrian earthquakes |
E580193
|
entity |
| Predicate | primaryHazard |
P1950
|
FINISHED |
| Object | strong ground shaking |
—
|
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: strong ground shaking | Statement: [1783 Calabrian earthquakes, primaryHazard, strong ground shaking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryHazard Context triple: [1783 Calabrian earthquakes, primaryHazard, strong ground shaking]
-
A.
primaryThreat
Indicates that one entity is the main or most significant source of danger, harm, or risk to another entity.
-
B.
hazardType
chosen
Indicates the specific kind or category of hazard associated with an entity or situation.
-
C.
primaryHeir
Indicates that one entity is the main or principal inheritor of another entity’s estate, title, or rights.
-
D.
secondaryHazardType
Indicates the type or category of a hazard that occurs as a secondary or consequential effect of a primary hazard or event.
-
E.
primaryCatch
Indicates that an entity is the main or most significant target, recipient, or object captured or obtained in a given context.
- 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_69e24601a9108190bc31e83833c980e4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1afd4cde48190b5e4eb162d772319 |
completed | April 29, 2026, 7:14 a.m. |
| PD | Predicate disambiguation | batch_69f118bcc0b08190b25a8dddfd461a0e |
completed | April 28, 2026, 8:29 p.m. |
Created at: April 17, 2026, 6:37 p.m.