Triple

T4532374
Position Surface form Disambiguated ID Type / Status
Subject Things to Come E106326 entity
Predicate producer P490 FINISHED
Object Alexander Korda E247981 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: Alexander Korda | Statement: [Things to Come, producer, Alexander Korda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alexander Korda
Context triple: [Things to Come, producer, Alexander Korda]
  • A. Alexander Korda chosen
    Alexander Korda was a pioneering Hungarian-British film producer and director who became a central figure in the development of the British film industry in the early 20th century.
  • B. Harry Saltzman
    Harry Saltzman was a Canadian-born film producer best known as the co-producer and co-creator of the James Bond film series.
  • C. Dean Zanuck
    Dean Zanuck is an American film producer and member of the prominent Zanuck filmmaking family, known for working on major Hollywood projects.
  • D. Walter Wanger
    Walter Wanger was an American film producer known for his work on numerous influential Hollywood films from the 1930s through the 1950s, often tackling socially conscious and ambitious subjects.
  • E. Daniel Selznick
    Daniel Selznick is an American film and television producer, known for his work in the mid-to-late 20th century and as part of the prominent Selznick entertainment family.
  • 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_69bd43f3d6e08190a91824f833d51bbe completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd579f27ac8190ae9a4252109e56e1 completed March 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdace3a81c8190963ea65fa3df23c0 completed March 20, 2026, 8:24 p.m.
Created at: March 20, 2026, 1:03 p.m.