Triple

T6673803
Position Surface form Disambiguated ID Type / Status
Subject Harvey E151799 entity
Predicate director P255 FINISHED
Object Henry Koster E56821 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: Henry Koster | Statement: [Harvey, director, Henry Koster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Henry Koster
Context triple: [Harvey, director, Henry Koster]
  • A. Henry Koster chosen
    Henry Koster was a German-born American film director best known for his work in Hollywood during the 1930s–1950s, including popular comedies, dramas, and family films.
  • B. Walt Dohrn
    Walt Dohrn is an American animator, voice actor, writer, and director best known for his creative leadership on DreamWorks Animation films such as the Trolls franchise.
  • C. Walter Scheib
    Walter Scheib was an American chef best known for serving as the White House Executive Chef for the Clinton and George W. Bush administrations.
  • D. Milt Schaffer
    Milt Schaffer was an American animator and story artist best known for his work on classic Disney cartoons in the mid-20th century.
  • E. Harold Hecht
    Harold Hecht was an American film producer and talent agent best known for co-founding Hecht-Hill-Lancaster and producing acclaimed mid-20th-century films such as "Marty."
  • 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_69c687f830bc81909eb8b04dbb8450b1 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b0f1d9d081909670f5c0b7389c0d completed March 27, 2026, 4:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69c70aeef0d881909da055735646dbaf completed March 27, 2026, 10:55 p.m.
Created at: March 27, 2026, 2:03 p.m.