Triple

T19190390
Position Surface form Disambiguated ID Type / Status
Subject Emile Berliner E469819 entity
Predicate familyName P18 FINISHED
Object Berliner 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: Berliner | Statement: [Emile Berliner, familyName, Berliner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berliner
Context triple: [Emile Berliner, familyName, Berliner]
  • A. Berliner chosen
    Berliner is a German-origin surname most notably associated with Emile Berliner, the inventor of the gramophone and a pioneer in sound recording technology.
  • B. Berlinchen
    Berlinchen is a small town in what is now Poland (formerly part of Germany) known historically as the birthplace of world chess champion Emanuel Lasker.
  • C. New Berlin
    New Berlin is a suburban city in Waukesha County, Wisconsin, located just west of Milwaukee and known for its residential communities and light industry.
  • D. New Berlin
    New Berlin is a small village in Sangamon County, Illinois, located near Springfield and known for its rural Midwestern character.
  • E. Berlin B
    Berlin B is one of the public transport fare zones in Berlin, covering the outer areas of the city beyond the central A zone.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f8a16e20819080baa5112f000b41 completed April 20, 2026, 9:57 a.m.
Created at: April 10, 2026, 12:07 p.m.