Triple

T7685623
Position Surface form Disambiguated ID Type / Status
Subject Folke Bernadotte E174108 entity
Predicate familyName P18 FINISHED
Object Bernadotte E278868 NE 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: Bernadotte | Statement: [Folke Bernadotte, familyName, Bernadotte]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bernadotte
Context triple: [Folke Bernadotte, familyName, Bernadotte]
  • A. Carl Johan Bernadotte
    Carl Johan Bernadotte was a Swedish prince who became a count of Wisborg after renouncing his royal succession rights to marry a commoner.
  • B. Olof Daniel Westling Bernadotte
    Olof Daniel Westling Bernadotte is a member of the Swedish royal family and the husband of Crown Princess Victoria of Sweden.
  • C. Ludvig
    Ludvig is a given name, primarily used in Scandinavian countries, that is a variant spelling of Ludwig.
  • D. Jean Baptiste Bernadotte chosen
    Jean Baptiste Bernadotte was a French marshal under Napoleon who became King Charles XIV John of Sweden and Norway, founding the still-reigning Bernadotte dynasty.
  • E. Gustaf
    Gustaf is the given name of Carl Gustaf Emil Mannerheim, the Finnish military leader and statesman who served as Commander-in-Chief during World War II and later as President of Finland.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69c6995840408190a19de6c51090f46f completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c7022118908190a3a93cfda79be0a4 completed March 27, 2026, 10:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8b4fda81881908144cebdd2696e63 completed March 29, 2026, 5:13 a.m.
Created at: March 27, 2026, 4:02 p.m.