Triple
T4121284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Knossos |
E92617
|
entity |
| Predicate | majorDestructionEvent |
P10547
|
FINISHED |
| Object | Thera eruption aftermath |
—
|
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: Thera eruption aftermath | Statement: [Knossos, majorDestructionEvent, Thera eruption aftermath]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorDestructionEvent Context triple: [Knossos, majorDestructionEvent, Thera eruption aftermath]
-
A.
timePeriodOfMajorDestruction
Indicates the time span during which a major destructive event affecting the subject occurred.
-
B.
majorCrisis
Indicates a severe, high-impact crisis or emergency situation affecting an entity or system.
-
C.
majorTectonicEvent
chosen
Indicates a significant geological event involving large-scale movement or deformation of the Earth's tectonic plates, such as major earthquakes, volcanic eruptions, or continental shifts.
-
D.
majorFlashpointIn
Indicates that an event, issue, or conflict serves as a primary source of tension or confrontation within a specified larger context or setting.
-
E.
hasCauseOfDestruction
Indicates that one entity is the cause or agent responsible for the destruction or damage of another entity.
- 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_69aed9685f70819086932777aec8d959 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69af0246e40081908ad6741a830ca68e |
completed | March 9, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_69af01867698819098e4144634b2ec4f |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:41 p.m.