Triple

T5386840
Position Surface form Disambiguated ID Type / Status
Subject Asparuh of Bulgaria E120220 entity
Predicate title P38 FINISHED
Object Khan E64995 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: Khan | Statement: [Asparuh of Bulgaria, title, Khan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Khan
Context triple: [Asparuh of Bulgaria, title, Khan]
  • A. Khan chosen
    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.
  • B. Kaan
    Kaan was a powerful Maya royal dynasty associated with the ancient city-state of Calakmul, known for its political and military rivalry with Tikal during the Classic period.
  • C. Kumail
    Kumail is a Pakistani-American comedian and actor best known for his work on the TV series "Silicon Valley" and the film "The Big Sick."
  • D. Hussain
    Hussain is a common given name and surname of Arabic origin, widely used in Muslim communities around the world.
  • E. Kahn
    Kahn is a surname most famously associated with Louis Kahn, the influential 20th-century architect known for his monumental and timeless modernist buildings.
  • 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_69bd46354c648190a38b26f107010a96 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd86f6f39c8190aa6af12370e3d12b completed March 20, 2026, 5:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf295352988190a48d3f9db56fcaf8 completed March 21, 2026, 11:27 p.m.
Created at: March 20, 2026, 2:03 p.m.