Triple

T27116458
Position Surface form Disambiguated ID Type / Status
Subject Charleston Seismic Zone E686858 entity
Predicate seismicRiskCategory P34010 FINISHED
Object significant for eastern United States 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: significant for eastern United States | Statement: [Charleston Seismic Zone, seismicRiskCategory, significant for eastern United States]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: seismicRiskCategory
Context triple: [Charleston Seismic Zone, seismicRiskCategory, significant for eastern United States]
  • A. seismicDesignCategory
    Indicates the classification of a structure’s required level of seismic resistance based on its expected exposure to earthquake forces.
  • B. earthquakeHazardLevel chosen
    Indicates the assessed degree of risk or potential impact from earthquakes associated with a given location or entity.
  • C. geologicHazardLevel
    Indicates the degree of potential danger or risk posed by geologic processes or conditions at a given location.
  • D. earthquakeDamageLevel
    Indicates the severity or extent of damage caused by an earthquake to a given subject.
  • E. earthquakeResistance
    Indicates how well an entity can withstand or remain functional during an earthquake without significant damage.
  • 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_69ef148c2b588190afc15b529f7af845 completed April 27, 2026, 7:47 a.m.
NER Named-entity recognition batch_69f624069afc8190916ff8dc2e4a3a1a completed May 2, 2026, 4:19 p.m.
PD Predicate disambiguation batch_69f620e0b37481909a280574decbd443 completed May 2, 2026, 4:05 p.m.
Created at: April 27, 2026, 8:56 a.m.