Triple

T19967701
Position Surface form Disambiguated ID Type / Status
Subject Ralph Behrens E479981 entity
Predicate familyName P18 FINISHED
Object Behrens
Behrens is a German-origin surname borne by numerous notable individuals in fields such as design, architecture, sports, and academia.
 E86796 NE FINISHED

How this triple was built (4 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: Behrens | Statement: [Ralph Behrens, familyName, Behrens]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Behrens
Context triple: [Ralph Behrens, familyName, Behrens]
  • A. Behrend
    Behrend is a German surname borne by various notable individuals across fields such as mathematics, politics, and the arts.
  • B. Bernsen
    Bernsen is a surname most notably associated with American actor Corbin Bernsen, known for his role on the television series "L.A. Law."
  • C. Braunshardt
    Braunshardt is a district of the town of Weiterstadt in the state of Hesse, Germany.
  • D. Behrent
    Behrent is a surname variant of Behrendt, typically of German origin.
  • E. Balkhausen
    Balkhausen is a district within the town of Kerpen in North Rhine-Westphalia, Germany.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Behrens
Triple: [Ralph Behrens, familyName, Behrens]
Generated description
Behrens is a German-origin surname borne by numerous notable individuals in fields such as design, architecture, sports, and academia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Behrens
Target entity description: Behrens is a German-origin surname borne by numerous notable individuals in fields such as design, architecture, sports, and academia.
  • A. Behrens chosen
    Behrens is a German surname most notably associated with influential architect and designer Peter Behrens.
  • B. Behrend
    Behrend is a German surname borne by various notable individuals across fields such as mathematics, politics, and the arts.
  • C. Bernsen
    Bernsen is a surname most notably associated with American actor Corbin Bernsen, known for his role on the television series "L.A. Law."
  • D. Braunshardt
    Braunshardt is a district of the town of Weiterstadt in the state of Hesse, Germany.
  • E. Behrent
    Behrent is a surname variant of Behrendt, typically of German origin.
  • F. None of above.

Provenance (5 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65bc6b0208190b1ae30be95712326 completed April 20, 2026, 5 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07fdd12e4c81908488a7a829ee7bc2 completed May 16, 2026, 5:17 a.m.
NEDg Description generation batch_6a07ff37a0508190af7cf7a045201338 completed May 16, 2026, 5:23 a.m.
NED2 Entity disambiguation (via description) batch_6a07ffad71508190a6636834b7f25434 completed May 16, 2026, 5:25 a.m.
Created at: April 10, 2026, 1:54 p.m.