Triple

T20383928
Position Surface form Disambiguated ID Type / Status
Subject The Match King E497910 entity
Predicate starring P1507 FINISHED
Object Harold Huber NE NERFINISHED

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: Harold Huber | Statement: [The Match King, starring, Harold Huber]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harold Huber
Context triple: [The Match King, starring, Harold Huber]
  • A. Harold Huber chosen
    Harold Huber was an American character actor known for his prolific work in 1930s and 1940s Hollywood films, often portraying suave or villainous supporting roles.
  • B. Harold Trosper
    Harold Trosper is known primarily as the brother of American screenwriter Guy Trosper.
  • C. Harold Wenstrom
    Harold Wenstrom was an American cinematographer active during the early 20th century, known for his work on numerous silent and early sound films.
  • D. Harold Burdick
    Harold Burdick is an alias used by Harold Finch, the reclusive billionaire and computer genius from the television series "Person of Interest."
  • E. Harold Huth
    Harold Huth was a British film director, producer, and occasional actor active in the mid-20th century, known for his work in the British studio system.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678b2ceec819091ad5205ee9b2174 completed April 20, 2026, 7:04 p.m.
Created at: April 16, 2026, 11:27 a.m.