Triple

T9251952
Position Surface form Disambiguated ID Type / Status
Subject Khazar Khaganate E222345 entity
Predicate headOfGovernmentTitle P329 FINISHED
Object Bek E415143 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: Bek | Statement: [Khazar Khaganate, headOfGovernmentTitle, Bek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bek
Context triple: [Khazar Khaganate, headOfGovernmentTitle, Bek]
  • A. Bek
    Bek is a short or informal given name, typically used as a diminutive of Rebekah.
  • B. Bey chosen
    A Bey was a provincial governor or chieftain in the Ottoman Empire, often wielding significant military and administrative authority.
  • C. BEK
    BEK is the IATA airport code for Bareilly Airport, a domestic airport serving the city of Bareilly in Uttar Pradesh, India.
  • D. Beketaten
    Beketaten was an ancient Egyptian princess of the 18th Dynasty, likely a daughter of Pharaoh Amenhotep III and Queen Tiye, who lived during the Amarna period.
  • E. Bec
    Bec is a historic Benedictine abbey in Normandy, France, renowned as a major medieval center of learning and monastic reform.
  • 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_69ca841d2b18819089f9faf5b2c2aec0 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd05fb1454819098f452846ca4ca61 completed April 1, 2026, 11:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0780650648190bc85452678268134 completed April 4, 2026, 2:31 a.m.
Created at: March 30, 2026, 7:31 p.m.