Triple

T2334793
Position Surface form Disambiguated ID Type / Status
Subject Paul Troost E44284 entity
Predicate partner P1136 FINISHED
Object Gerdy Troost E256965 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: Gerdy Troost | Statement: [Paul Troost, partner, Gerdy Troost]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gerdy Troost
Context triple: [Paul Troost, partner, Gerdy Troost]
  • A. Gerdy Troost chosen
    Gerdy Troost was a German interior designer and architect closely associated with National Socialist architecture and the continuation of her husband Paul Troost’s work after his death.
  • B. Coosje van Bruggen
    Coosje van Bruggen was a Dutch-American sculptor and art historian best known for her large-scale public art collaborations with her husband Claes Oldenburg.
  • C. Ella van Heemstra
    Ella van Heemstra was a Dutch baroness and socialite best known as the mother of iconic actress Audrey Hepburn.
  • D. Karin Daan
    Karin Daan is a Dutch artist and designer best known for creating the Homomonument in Amsterdam, one of the world’s first monuments commemorating LGBTQ+ persecution and struggle.
  • E. Toni Merkens
    Toni Merkens was a German track cyclist best known for winning the gold medal in the sprint event at the 1936 Berlin Olympics.
  • 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_69a889132b488190bbb43ad4780ddd92 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abc687362c8190a55b3d6cb1580d56 completed March 7, 2026, 6:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae961adfdc8190bf79d479d8207599 completed March 9, 2026, 9:42 a.m.
Created at: March 4, 2026, 7:51 p.m.