Triple

T383157
Position Surface form Disambiguated ID Type / Status
Subject Catherine E8723 entity
Predicate hasVariant P455 FINISHED
Object Kaja
Kaja is a given name used as a variant of Catherine in some languages and cultures.
 E58213 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: Kaja | Statement: [Catherine, hasVariant, Kaja]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kaja
Context triple: [Catherine, hasVariant, Kaja]
  • A. Mila
    Mila is a leading artificial intelligence research institute based in Quebec, renowned for its work in deep learning and machine learning.
  • B. Karol
    Karol is the given name of Pope John Paul II, the Polish-born head of the Catholic Church from 1978 to 2005.
  • C. Katrin
    Katrin is a feminine given name, commonly used in various European countries, that is a variant of the name Catherine.
  • D. Alara Kitan
    Alara Kitan is a young, super-strong Xelayan officer who serves as the chief of security aboard the exploratory spaceship in the sci-fi comedy-drama series "The Orville."
  • E. Karinska
    Karinska was a renowned 20th-century costume designer best known for her influential work in ballet and theater, particularly with the New York City Ballet.
  • 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: Kaja
Triple: [Catherine, hasVariant, Kaja]
Generated description
Kaja is a given name used as a variant of Catherine in some languages and cultures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kaja
Target entity description: Kaja is a given name used as a variant of Catherine in some languages and cultures.
  • A. Mila
    Mila is a leading artificial intelligence research institute based in Quebec, renowned for its work in deep learning and machine learning.
  • B. Karol
    Karol is the given name of Pope John Paul II, the Polish-born head of the Catholic Church from 1978 to 2005.
  • C. Katrin chosen
    Katrin is a feminine given name, commonly used in various European countries, that is a variant of the name Catherine.
  • D. Alara Kitan
    Alara Kitan is a young, super-strong Xelayan officer who serves as the chief of security aboard the exploratory spaceship in the sci-fi comedy-drama series "The Orville."
  • E. Karinska
    Karinska was a renowned 20th-century costume designer best known for her influential work in ballet and theater, particularly with the New York City Ballet.
  • F. None of above.

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_69a2e7f47dd08190a4e294ccbbe46cd4 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec40ff8c81909306eb2dfe1512af completed Feb. 28, 2026, 1:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4b238cd848190b5d9152d63dbe71c completed March 1, 2026, 9:40 p.m.
NEDg Description generation batch_69a4b4dd7fe48190b6dd29b2b806a2a5 completed March 1, 2026, 9:51 p.m.
NED2 Entity disambiguation (via description) batch_69a4b52a79548190ac8ff1b7dd9ccbe5 completed March 1, 2026, 9:52 p.m.
Created at: Feb. 28, 2026, 1:08 p.m.