Triple

T8191236
Position Surface form Disambiguated ID Type / Status
Subject Irving Kahn E191311 entity
Predicate familyName P18 FINISHED
Object Kahn E126770 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: Kahn | Statement: [Irving Kahn, familyName, Kahn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kahn
Context triple: [Irving Kahn, familyName, Kahn]
  • A. Kahn chosen
    Kahn is a surname most famously associated with Louis Kahn, the influential 20th-century architect known for his monumental and timeless modernist buildings.
  • B. KAHN
    KAHN is the ICAO airport code for Athens Ben Epps Airport, a public airport serving Athens, Georgia, in the United States.
  • C. Kleinburg
    Kleinburg is a historic, affluent village within the city of Vaughan, Ontario, known for its charming main street and the McMichael Canadian Art Collection.
  • D. Kahle
    Kahle is a surname most notably associated with Brewster Kahle, the American computer engineer and digital librarian who founded the Internet Archive.
  • E. Khan
    Khan is a common surname of Central and South Asian origin historically associated with nobility and leadership, now widely used across Muslim and other communities worldwide.
  • 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_69ca82c5b6948190a583c096fb0a6c71 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4da4a6f08190be8088a28d928341 completed March 31, 2026, 4:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69cced979d408190851088c6d3f4df24 completed April 1, 2026, 10:04 a.m.
Created at: March 30, 2026, 5:42 p.m.