Triple

T9199165
Position Surface form Disambiguated ID Type / Status
Subject Marjorie Tallchief E220791 entity
Predicate partner P1136 FINISHED
Object George Skibine E784539 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: George Skibine | Statement: [Marjorie Tallchief, partner, George Skibine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Skibine
Context triple: [Marjorie Tallchief, partner, George Skibine]
  • A. George Skibine chosen
    George Skibine was a prominent ballet dancer and choreographer of the mid-20th century, known for his work with major companies such as the Ballet Russe de Monte Carlo and the Paris Opera Ballet.
  • B. James Ashmore Creelman
    James Ashmore Creelman was an American screenwriter best known for his work on early 1930s adventure and horror films, including the classic monster movie King Kong.
  • C. Georgy Shpagin
    Georgy Shpagin was a Soviet weapons designer best known for creating some of the Red Army’s most widely used submachine guns during World War II.
  • D. Aleksei Bilderling
    Aleksei Bilderling was a Russian Imperial Army general best known for his leadership role in the Russo-Japanese War, particularly during the Battle of Mukden.
  • E. Charles Volz
    Charles Volz was an architect associated with the design and development of the American Museum of Natural History in New York City.
  • 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_69ca83e8e9248190862cf3e41693b310 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccd880ab808190aa785a5f1e5d5976 completed April 1, 2026, 8:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69d065d8f358819085dec73f25fd5746 completed April 4, 2026, 1:14 a.m.
Created at: March 30, 2026, 7:25 p.m.