Triple

T18891883
Position Surface form Disambiguated ID Type / Status
Subject Samu Kerevi E462109 entity
Predicate familyName P18 FINISHED
Object Kerevi
Kerevi is a surname most prominently associated with Samu Kerevi, a professional rugby union player who has represented Australia internationally.
 E1347848 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: Kerevi | Statement: [Samu Kerevi, familyName, Kerevi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kerevi
Context triple: [Samu Kerevi, familyName, Kerevi]
  • A. Kungara
    Kungara is an alternative name for the Fur language, a Nilo-Saharan language spoken primarily by the Fur people of western Sudan.
  • B. Kori
    Kori is a given name, often used as a variant spelling of Cory or Corey.
  • C. Kori
    Kori is a dialect of the Kaili language, an Austronesian language spoken in Central Sulawesi, Indonesia.
  • D. Kerchak
    Kerchak is the powerful and initially distrustful leader of the gorilla troop who serves as a central paternal figure in Disney’s Tarzan stories.
  • E. Kamviri
    Kamviri is a dialect of the Nuristani Kati language spoken by the Kam people in parts of northeastern Afghanistan and northwestern Pakistan.
  • 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: Kerevi
Triple: [Samu Kerevi, familyName, Kerevi]
Generated description
Kerevi is a surname most prominently associated with Samu Kerevi, a professional rugby union player who has represented Australia internationally.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kerevi
Target entity description: Kerevi is a surname most prominently associated with Samu Kerevi, a professional rugby union player who has represented Australia internationally.
  • A. Kungara
    Kungara is an alternative name for the Fur language, a Nilo-Saharan language spoken primarily by the Fur people of western Sudan.
  • B. Kori
    Kori is a dialect of the Kaili language, an Austronesian language spoken in Central Sulawesi, Indonesia.
  • C. Kori
    Kori is a given name, often used as a variant spelling of Cory or Corey.
  • D. Kerchak
    Kerchak is the powerful and initially distrustful leader of the gorilla troop who serves as a central paternal figure in Disney’s Tarzan stories.
  • E. Kamviri
    Kamviri is a dialect of the Nuristani Kati language spoken by the Kam people in parts of northeastern Afghanistan and northwestern Pakistan.
  • 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_69d8dcfc3430819095ee6fc0eb4c06a5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c47bbf908190b141e98e3468e908 completed April 20, 2026, 6:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0582b75c708190b8ba4cb05a475899 completed May 14, 2026, 8:07 a.m.
NEDg Description generation batch_6a058659f5988190a4c5921a74a5e917 completed May 14, 2026, 8:22 a.m.
NED2 Entity disambiguation (via description) batch_6a0586d4df588190a33e60b103a5847e completed May 14, 2026, 8:24 a.m.
Created at: April 10, 2026, 11:58 a.m.