Triple

T4867632
Position Surface form Disambiguated ID Type / Status
Subject Cohen E109009 entity
Predicate scriptVariant P4680 FINISHED
Object Kahana
Kahana is a variant form of the Jewish surname Cohen, often used in Ashkenazi communities.
 E476980 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: Kahana | Statement: [Cohen, scriptVariant, Kahana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kahana
Context triple: [Cohen, scriptVariant, Kahana]
  • A. Dairen
    Dairen, now known as Dalian, is a major port city in northeastern China that historically served as an important strategic and commercial hub under various foreign leases and administrations.
  • B. Kandel
    Kandel is a prominent mountain in Germany’s Black Forest region, known for its scenic views and outdoor recreation opportunities.
  • C. Migdal
    Migdal is an ancient town on the western shore of the Sea of Galilee in northern Israel, traditionally identified with the biblical Magdala and known as the hometown of Mary Magdalene.
  • D. Kingisepp
    Kingisepp is a town in northwestern Russia near the Estonian border, known for its industrial base and historical roots dating back to the 14th century.
  • E. Radwar
    Radwar is a prominent Polish defense company known for developing and producing advanced radar and air-defense systems.
  • 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: Kahana
Triple: [Cohen, scriptVariant, Kahana]
Generated description
Kahana is a variant form of the Jewish surname Cohen, often used in Ashkenazi communities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kahana
Target entity description: Kahana is a variant form of the Jewish surname Cohen, often used in Ashkenazi communities.
  • A. Dairen
    Dairen, now known as Dalian, is a major port city in northeastern China that historically served as an important strategic and commercial hub under various foreign leases and administrations.
  • B. Kandel
    Kandel is a prominent mountain in Germany’s Black Forest region, known for its scenic views and outdoor recreation opportunities.
  • C. Migdal
    Migdal is an ancient town on the western shore of the Sea of Galilee in northern Israel, traditionally identified with the biblical Magdala and known as the hometown of Mary Magdalene.
  • D. Kingisepp
    Kingisepp is a town in northwestern Russia near the Estonian border, known for its industrial base and historical roots dating back to the 14th century.
  • E. Radwar
    Radwar is a prominent Polish defense company known for developing and producing advanced radar and air-defense systems.
  • 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_69bd440d96a48190b0c87069adef2af1 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6d7bb0b88190bbc24498619910fc completed March 20, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69be67e5d96c8190b2a509d9fb81211a completed March 21, 2026, 9:41 a.m.
NEDg Description generation batch_69be693b36b08190a0de648f0c5bdc60 completed March 21, 2026, 9:47 a.m.
NED2 Entity disambiguation (via description) batch_69be69a16b0c8190b0a787bb54b31fc3 completed March 21, 2026, 9:49 a.m.
Created at: March 20, 2026, 1:26 p.m.