Triple

T18711467
Position Surface form Disambiguated ID Type / Status
Subject Starman E457523 entity
Predicate starring P1507 FINISHED
Object Richard Jaeckel 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: Richard Jaeckel | Statement: [Starman, starring, Richard Jaeckel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard Jaeckel
Context triple: [Starman, starring, Richard Jaeckel]
  • A. Richard Jaeckel chosen
    Richard Jaeckel was an American character actor known for his tough, rugged roles in numerous war films, Westerns, and crime dramas from the 1940s through the 1990s.
  • B. Richard Schayer
    Richard Schayer was an American screenwriter prominent during the silent and early sound eras of Hollywood, contributing to numerous films across various genres.
  • C. Richard Lindheim
    Richard Lindheim was an American television producer and executive best known for co-creating the crime drama series "The Equalizer" and for his influential roles at major networks and studios.
  • D. Richard Reitinger
    Richard Reitinger is a German screenwriter best known for co-writing Wim Wenders’ acclaimed film "Wings of Desire."
  • E. Richard Klubeck
    Richard Klubeck is a film producer best known for his work on the acclaimed independent movie "Garden State."
  • 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5671b34508190b6180f7d6ad50a58 completed April 19, 2026, 11:36 p.m.
Created at: April 10, 2026, 11:50 a.m.