Triple

T20723951
Position Surface form Disambiguated ID Type / Status
Subject Erna Solberg E509387 entity
Predicate givenName P17 FINISHED
Object Erna NE NERFINISHED

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: Erna | Statement: [Erna Solberg, givenName, Erna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erna
Context triple: [Erna Solberg, givenName, Erna]
  • A. Erna chosen
    Erna is the given name of Erna Schneider Hoover, an American mathematician and pioneering computer scientist known for revolutionizing telephone switching systems.
  • B. Ema
    Ema is a given name used as a variant spelling of Emma in various languages and cultures.
  • C. Ema
    Ema is an Austronesian language spoken primarily in East Timor, also known as the Kemak language.
  • D. Maritta
    Maritta is a feminine given name, typically considered a variant of names like Marita or Maria used in various European cultures.
  • E. Magdalena
    Magdalena is a historic town in the Mexican state of Jalisco, known for its role in the tequila-producing region and its proximity to agave landscapes and traditional distilleries.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1e662f08190917ee043612d413e completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:28 p.m.