Triple

T8189870
Position Surface form Disambiguated ID Type / Status
Subject Blanca E191275 entity
Predicate hasCognate P2525 FINISHED
Object Blanka
Blanka is a given name used in various Slavic and Central European countries, equivalent to the name Blanca or Bianca.
E718191 NE FINISHED

How this triple was built (4 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: Blanka | Statement: [Blanca, hasCognate, Blanka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blanka
Context triple: [Blanca, hasCognate, Blanka]
  • A. Nessarose
    Nessarose is a character from the musical and novel "Wicked," known as Elphaba's wheelchair-bound, deeply devout sister who becomes the Wicked Witch of the East.
  • B. Daizy
    Daizy is an alternative spelling or variant form of the given name Daisy, often used as a personal name.
  • C. Marth
    Marth is a heroic prince and skilled swordsman from Nintendo's Fire Emblem series, widely recognized as one of its earliest and most iconic protagonists.
  • D. Katarina Taikon
    Katarina Taikon was a prominent Swedish Romani activist and author, best known for her influential autobiographical "Katitzi" book series that highlighted Roma rights and experiences.
  • E. Ness
    Ness is a remote crofting and fishing community at the northern tip of the Isle of Lewis in Scotland’s Outer Hebrides.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Blanka
Triple: [Blanca, hasCognate, Blanka]
Generated description
Blanka is a given name used in various Slavic and Central European countries, equivalent to the name Blanca or Bianca.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Blanka
Target entity description: Blanka is a given name used in various Slavic and Central European countries, equivalent to the name Blanca or Bianca.
  • A. Nessarose
    Nessarose is a character from the musical and novel "Wicked," known as Elphaba's wheelchair-bound, deeply devout sister who becomes the Wicked Witch of the East.
  • B. Daizy
    Daizy is an alternative spelling or variant form of the given name Daisy, often used as a personal name.
  • C. Marth
    Marth is a heroic prince and skilled swordsman from Nintendo's Fire Emblem series, widely recognized as one of its earliest and most iconic protagonists.
  • D. Katarina Taikon
    Katarina Taikon was a prominent Swedish Romani activist and author, best known for her influential autobiographical "Katitzi" book series that highlighted Roma rights and experiences.
  • E. Ness
    Ness is a remote crofting and fishing community at the northern tip of the Isle of Lewis in Scotland’s Outer Hebrides.
  • F. None of above. chosen

Provenance (5 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_69ca82c5b6948190a583c096fb0a6c71 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4da0e1288190b9c7c1d3b9a98830 completed March 31, 2026, 4:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69cced8da28c81909c34c0103da68f0f completed April 1, 2026, 10:03 a.m.
NEDg Description generation batch_69ccf1b5f95481909fdb08d00d06023e completed April 1, 2026, 10:21 a.m.
NED2 Entity disambiguation (via description) batch_69cd059457788190a900402ee4cd50d5 completed April 1, 2026, 11:46 a.m.
Created at: March 30, 2026, 5:41 p.m.