Triple

T20535685
Position Surface form Disambiguated ID Type / Status
Subject Erich Kästner E504189 entity
Predicate wrote P2831 FINISHED
Object Lottie and Lisa 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: Lottie and Lisa | Statement: [Erich Kästner, wrote, Lottie and Lisa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lottie and Lisa
Context triple: [Erich Kästner, wrote, Lottie and Lisa]
  • A. Lottie and Lisa chosen
    Lottie and Lisa is a 1949 German children's novel by Erich Kästner about identical twin girls separated at birth who meet at a summer camp and switch places to reunite their divorced parents.
  • B. Wendy & Lisa
    Wendy & Lisa is an American musical duo best known for their work with Prince and The Revolution and their subsequent career composing and performing their own eclectic pop, rock, and soundtrack music.
  • C. Liz
    Liz is a common shortened form or nickname for the given name Elizabeth.
  • D. Jenny and Johnny
    Jenny and Johnny is an indie rock duo formed by singer-songwriter Jenny Lewis and musician Johnathan Rice, known for their melodic, harmony-rich songs.
  • E. Lizz
    Lizz is a feminine given name, often used as a shortened form of Elizabeth.
  • 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a06ed3088190bd01a95672b01ad6 completed April 20, 2026, 9:53 p.m.
Created at: April 16, 2026, 11:37 a.m.