Triple

T866864
Position Surface form Disambiguated ID Type / Status
Subject People E18721 entity
Predicate founder P104 FINISHED
Object Andrew Heiskell E51606 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: Andrew Heiskell | Statement: [People, founder, Andrew Heiskell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew Heiskell
Context triple: [People, founder, Andrew Heiskell]
  • A. Andrew Heiskell chosen
    Andrew Heiskell was an American publishing executive and philanthropist best known as a longtime leader of Time Inc. and a prominent figure in New York’s cultural and civic life.
  • B. Louis Hellman
    Louis Hellman is a British architect and cartoonist best known for his satirical illustrations about architecture and the built environment.
  • C. Dean Riesner
    Dean Riesner was an American screenwriter best known for his work on films such as "Dirty Harry" and "Play Misty for Me."
  • D. Philip Moeller
    Philip Moeller was an American theater director, playwright, and producer best known as a co-founder and key creative force behind New York’s influential Theatre Guild in the early 20th century.
  • E. Joseph Wechsler
    Joseph Wechsler was an individual of sufficient local or historical significance to be recognized as a notable burial at Mount Olivet Cemetery in Frederick, Maryland.
  • 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_69a4938ce8688190a24bdfef82ba7d21 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ac7e12b0819084d25b9a66888a91 completed March 1, 2026, 9:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69adfb7b11fc8190b90361eed3b90f94 completed March 8, 2026, 10:43 p.m.
Created at: March 1, 2026, 7:39 p.m.