Triple

T21303664
Position Surface form Disambiguated ID Type / Status
Subject Karl Zerbe E525133 entity
Predicate familyName P18 FINISHED
Object Zerbe E869372 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: Zerbe | Statement: [Karl Zerbe, familyName, Zerbe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zerbe
Context triple: [Karl Zerbe, familyName, Zerbe]
  • A. Zerbe chosen
    Zerbe is a surname of German origin borne by various notable individuals, including American actor Anthony Zerbe.
  • B. Eisele
    Eisele is a surname most notably associated with Donn F. Eisele, an American astronaut who flew on the Apollo 7 mission.
  • C. Fahrenkopf
    Fahrenkopf is a surname most prominently associated with Frank J. Fahrenkopf Jr., an American lawyer, lobbyist, and former chairman of the Republican National Committee.
  • D. Nitzschka
    Nitzschka is a village and district of the town of Wurzen in the Free State of Saxony, Germany.
  • E. Gotschlich
    Gotschlich is the surname of Emil C. Gotschlich, an American physician and microbiologist known for his pioneering work on meningococcal vaccines.
  • 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_69e0b518b8948190ad69cf9a8784d397 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7385da340819083c07f353f2142b0 completed April 21, 2026, 8:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a099ed32130819081479d9845d74ac3 completed May 17, 2026, 10:56 a.m.
Created at: April 16, 2026, 4:05 p.m.