Triple

T21824689
Position Surface form Disambiguated ID Type / Status
Subject Wilhelm Bleek E538819 entity
Predicate spouse P13 FINISHED
Object Fanny Bleek 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: Fanny Bleek | Statement: [Wilhelm Bleek, spouse, Fanny Bleek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fanny Bleek
Context triple: [Wilhelm Bleek, spouse, Fanny Bleek]
  • A. Fanny Bleek chosen
    Fanny Bleek was the wife of German linguist and philologist Wilhelm Bleek, known for his pioneering work on African languages.
  • B. Mary van der Linden
    Mary van der Linden is the emotionally conflicted central figure of Sebastian Faulks's novel "On Green Dolphin Street," whose life and marriage are upended by an intense love affair in Cold War-era Washington, D.C.
  • C. Saartje van der Made
    Saartje van der Made is a Dutch architect known for her partnership role at the prominent architecture firm Benthem Crouwel Architekten.
  • D. Douwes Dekker
    Douwes Dekker is a Dutch surname most famously associated with the writer and anti-colonial critic Multatuli (Eduard Douwes Dekker).
  • E. Margriet Francisca
    Margriet Francisca is a Dutch princess, the third daughter of former Queen Juliana and Prince Bernhard of the Netherlands, known for her public service and charitable work.
  • 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_69e0c475038c8190abb9b1a20eb8ff50 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f091307d408190a92b65c3f39682a8 completed April 28, 2026, 10:51 a.m.
Created at: April 16, 2026, 6:54 p.m.