Triple

T19797032
Position Surface form Disambiguated ID Type / Status
Subject Jenny Lind E475570 entity
Predicate familyName P18 FINISHED
Object Lind 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: Lind | Statement: [Jenny Lind, familyName, Lind]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lind
Context triple: [Jenny Lind, familyName, Lind]
  • A. Lind chosen
    Lind is a surname of German and Scandinavian origin borne by various notable individuals across fields such as the arts, politics, and academia.
  • B. Linder
    Linder is a river in Bavaria, Germany, known as a headwater stream of the Ammer that flows through the Ammergau Alps.
  • C. Linder
    Linder is a surname of likely European origin borne by various individuals and families.
  • D. Lindberg
    Lindberg is a small municipality in the Regen district of Bavaria, Germany, known for its location in the Bavarian Forest region.
  • E. Lindman
    Lindman is a Swedish surname most notably associated with Arvid Lindman, a prominent early 20th-century Swedish politician and two-time Prime Minister.
  • 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e653c723548190ac9bfaecaf8afb13 completed April 20, 2026, 4:26 p.m.
Created at: April 10, 2026, 1:49 p.m.