Triple

T25859141
Position Surface form Disambiguated ID Type / Status
Subject International Geomagnetic Reference Field E651434 entity
Predicate doesNotModel P23080 FINISHED
Object external magnetic field sources 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: external magnetic field sources | Statement: [International Geomagnetic Reference Field, doesNotModel, external magnetic field sources]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: doesNotModel
Context triple: [International Geomagnetic Reference Field, doesNotModel, external magnetic field sources]
  • A. doesNotUse
    Indicates that one entity intentionally refrains from employing, utilizing, or relying on another entity, method, or resource.
  • B. doesNot
    Indicates that a specified entity lacks, refrains from, or fails to perform a particular action or exhibit a particular property in relation to another entity or context.
  • C. notUsedOnModel
    Indicates that a particular item, component, or feature is not applied, installed, or utilized on the specified model.
  • D. doesNotDefine chosen
    Indicates that one entity does not provide a definition, specification, or determining description for another entity.
  • E. doesNotTreat
    Indicates that one entity refrains from or fails to provide treatment or care to 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_69e7ab3a199c81909227cb964cacfe24 completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f6026a80208190a8b1fae20d6ed906 completed May 2, 2026, 1:55 p.m.
PD Predicate disambiguation batch_69f4a0fed15881909b789251fe5d8d45 completed May 1, 2026, 12:47 p.m.
Created at: April 22, 2026, 8:04 a.m.