Triple

T20102769
Position Surface form Disambiguated ID Type / Status
Subject Rosemarie Trockel E496587 entity
Predicate familyName P18 FINISHED
Object Trockel 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: Trockel | Statement: [Rosemarie Trockel, familyName, Trockel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trockel
Context triple: [Rosemarie Trockel, familyName, Trockel]
  • A. Trockel chosen
    Trockel is the surname of Rosemarie Trockel, a prominent German conceptual artist known for her innovative textile and multimedia works.
  • B. Trocka
    Trocka is a Warsaw Metro station serving the Targówek district in Poland.
  • C. Trappier
    Trappier is a French surname most notably associated with Éric Trappier, the CEO of Dassault Aviation.
  • D. Trost
    Trost is a surname most notably associated with Barry M. Trost, an influential American chemist known for his work in organic synthesis and the concept of atom economy.
  • E. Trockener Steg
    Trockener Steg is a high-altitude mountain station and ski area hub above Zermatt, Switzerland, serving as a key junction for cable cars and access to the surrounding glaciers and peaks.
  • 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_69da626eee3881909f3454986d4a6511 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6667170a4819085d07a4188ded541 completed April 20, 2026, 5:46 p.m.
Created at: April 11, 2026, 11:27 p.m.