Triple

T5038392
Position Surface form Disambiguated ID Type / Status
Subject Leo Beranek E113483 entity
Predicate familyName P18 FINISHED
Object Beranek E113483 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: Beranek | Statement: [Leo Beranek, familyName, Beranek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Beranek
Context triple: [Leo Beranek, familyName, Beranek]
  • A. Beranek chosen
    Beranek is a surname most notably associated with Leo Beranek, an American acoustics expert and co-founder of the engineering firm Bolt, Beranek and Newman (BBN).
  • B. Oberholtzer
    Oberholtzer is a German-origin surname, often associated with Mennonite and Amish families, that serves as a variant of the Overholt family name.
  • C. Takács
    Takács is a Hungarian surname borne by numerous notable individuals across fields such as sports, music, and academia.
  • D. Krafft
    Krafft is a variant spelling of the surname Kraft, which is of German origin and borne by various notable individuals.
  • E. Bergensten
    Bergensten is the surname of Jens Bergensten, the Swedish video game programmer and lead developer known for his work on Minecraft.
  • 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_69bd44384298819089c49e7c330ec7b8 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd73daaa788190b670f6c328bfa44f completed March 20, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69be9c7c8ba881908240c7f338ad9784 completed March 21, 2026, 1:26 p.m.
Created at: March 20, 2026, 1:37 p.m.