Triple

T18103205
Position Surface form Disambiguated ID Type / Status
Subject Kehaya Bey E433279 entity
Predicate title P38 FINISHED
Object Bey NE NERFINISHED

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: Bey | Statement: [Kehaya Bey, title, Bey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bey
Context triple: [Kehaya Bey, title, Bey]
  • A. Bey chosen
    A Bey was a provincial governor or chieftain in the Ottoman Empire, often wielding significant military and administrative authority.
  • B. BEY
    BEY is the IATA airport code for Beirut–Rafic Hariri International Airport, the main international gateway to Lebanon’s capital city.
  • C. Bek
    Bek is a short or informal given name, typically used as a diminutive of Rebekah.
  • D. Beyton
    Beyton is a small rural village and civil parish in the English county of Suffolk, known for its traditional village green and historic buildings.
  • E. Bessi
    The Bessi were an ancient Thracian tribe known from classical sources for inhabiting mountainous regions and serving as fierce, often rebellious, warriors and priests.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b90916008190a1f110bd7ced5473 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ddb7be948190b4ed4586f731d6f2 completed April 19, 2026, 1:50 p.m.
Created at: April 10, 2026, 10:28 a.m.