Triple

T19850507
Position Surface form Disambiguated ID Type / Status
Subject Kohen E476978 entity
Predicate surnameVariant P16885 FINISHED
Object Kohane
Kohane is a surname that likely originates as a variant of the Jewish priestly name "Kohen" (or "Cohen"), traditionally associated with descendants of the biblical priestly class.
 E1398037 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: Kohane | Statement: [Kohen, surnameVariant, Kohane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kohane
Context triple: [Kohen, surnameVariant, Kohane]
  • A. Kotane
    Kotane is a surname most notably associated with Moses Kotane, a prominent South African anti-apartheid activist and leader of the South African Communist Party.
  • B. Kagee
    Kagee is the former name of Chiayi City, a historic urban center in southwestern Taiwan.
  • C. Kashira
    Kashira is a historic town in Russia, located south of Moscow on the Oka River and known as a regional industrial and transport center.
  • D. Sorabi
    Sorabi is a traditional Indonesian pancake made from rice flour and coconut milk, commonly enjoyed as a snack or street food.
  • E. Koubia
    Koubia is a town in the Middle Guinea region of Guinea that serves as an important local administrative and commercial center.
  • 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: Kohane
Triple: [Kohen, surnameVariant, Kohane]
Generated description
Kohane is a surname that likely originates as a variant of the Jewish priestly name "Kohen" (or "Cohen"), traditionally associated with descendants of the biblical priestly class.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kohane
Target entity description: Kohane is a surname that likely originates as a variant of the Jewish priestly name "Kohen" (or "Cohen"), traditionally associated with descendants of the biblical priestly class.
  • A. Kotane
    Kotane is a surname most notably associated with Moses Kotane, a prominent South African anti-apartheid activist and leader of the South African Communist Party.
  • B. Kagee
    Kagee is the former name of Chiayi City, a historic urban center in southwestern Taiwan.
  • C. Kashira
    Kashira is a historic town in Russia, located south of Moscow on the Oka River and known as a regional industrial and transport center.
  • D. Sorabi
    Sorabi is a traditional Indonesian pancake made from rice flour and coconut milk, commonly enjoyed as a snack or street food.
  • E. Koubia
    Koubia is a town in the Middle Guinea region of Guinea that serves as an important local administrative and commercial center.
  • 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_69d8e51d39d081909bcfafeaaf3d2fcc completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65867b5408190bbd12ca567c4705f completed April 20, 2026, 4:46 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07d44098188190b2627bbf3695495d completed May 16, 2026, 2:19 a.m.
NEDg Description generation batch_6a07d51bda3c81908575cd41a212c108 completed May 16, 2026, 2:23 a.m.
NED2 Entity disambiguation (via description) batch_6a07d5d7c4bc8190ab189fa556a956d7 completed May 16, 2026, 2:26 a.m.
Created at: April 10, 2026, 1:51 p.m.