Triple

T1862468
Position Surface form Disambiguated ID Type / Status
Subject Mitchell Kapor E34845 entity
Predicate hasSurname P18 FINISHED
Object Kapor E34845 NE FINISHED

How this triple was built (2 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: Kapor | Statement: [Mitchell Kapor, hasSurname, Kapor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kapor
Context triple: [Mitchell Kapor, hasSurname, Kapor]
  • A. Kapor chosen
    Kapor is the surname of Mitchell Kapor, an American entrepreneur best known for founding the software company Lotus Development Corporation.
  • B. Kierling
    Kierling is a small locality in Lower Austria best known as the place where writer Franz Kafka spent his final days and died.
  • C. Jopara
    Jopara is a mixed language spoken in Paraguay that blends Guaraní and Spanish in everyday communication.
  • D. Sokar
    Sokar is an ancient Egyptian funerary god associated with the Memphite necropolis, the afterlife, and aspects of death and rebirth.
  • E. Kolis
    The Kolis are a prominent fishing and agrarian community of western India, particularly associated with coastal and riverine regions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb09e714881909cef0f7e77b5b3b9 completed March 7, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69addf4ecdc08190a264b358d3883f70 completed March 8, 2026, 8:42 p.m.
Created at: March 4, 2026, 7:34 p.m.