Triple

T4143948
Position Surface form Disambiguated ID Type / Status
Subject Johanna Spyri E89337 entity
Predicate familyName P18 FINISHED
Object Spyri E89337 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: Spyri | Statement: [Johanna Spyri, familyName, Spyri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Spyri
Context triple: [Johanna Spyri, familyName, Spyri]
  • A. Spyri chosen
    Spyri is the surname of Johanna Spyri, the Swiss author best known for creating the classic children's book character Heidi.
  • B. Spiro
    Spiro is a masculine given name most notably borne by Spiro Agnew, the 39th vice president of the United States.
  • C. Psiri
    Psiri is a lively historic neighborhood in central Athens known for its vibrant nightlife, traditional tavernas, and artistic atmosphere.
  • D. Dora Riparia
    Dora Riparia is a river in northwestern Italy that flows through the city of Turin before joining the Po River.
  • E. Tulp
    Tulp is the surname of Nicolaes Tulp, a notable 17th-century Dutch physician and Amsterdam civic leader famously depicted in Rembrandt’s painting "The Anatomy Lesson of Dr. Nicolaes Tulp."
  • 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_69aed95785788190ae75bcf0cd1cafdf completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af025d2984819095f299327cc399d5 completed March 9, 2026, 5:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69b576d2f1788190847d38a384abbe67 completed March 14, 2026, 2:55 p.m.
Created at: March 9, 2026, 3:43 p.m.