Triple

T6362616
Position Surface form Disambiguated ID Type / Status
Subject Topsy-Turvy E143146 entity
Predicate editedBy P1954 FINISHED
Object Robin Sales E126851 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: Robin Sales | Statement: [Topsy-Turvy, editedBy, Robin Sales]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robin Sales
Context triple: [Topsy-Turvy, editedBy, Robin Sales]
  • A. Robin Sales chosen
    Robin Sales is an editor known for working on the film "Wild Target."
  • B. Phil Sellers
    Phil Sellers was a standout forward for Rutgers University in the 1970s who became the program’s all-time leading scorer and led the team to the 1976 Final Four.
  • C. Michael L. Sale
    Michael L. Sale is a film editor known for his work on major Hollywood comedies, including the hit movie "Bridesmaids."
  • D. Christopher Allen Sale
    Christopher Allen Sale is an American professional baseball pitcher known for his dominant left-handed pitching and multiple MLB All-Star selections.
  • E. Carl Piper
    Carl Piper was a prominent Swedish statesman and close adviser to King Charles XII during the Great Northern War.
  • 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_69c008d7a9c4819098d647ec47776917 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0680c02b481908618317566e31a5c completed March 22, 2026, 10:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69c62d73a6ac8190a02602c3506e4226 completed March 27, 2026, 7:10 a.m.
Created at: March 22, 2026, 4:32 p.m.