Triple

T13911717
Position Surface form Disambiguated ID Type / Status
Subject The Meg E334512 entity
Predicate screenwriter P2831 FINISHED
Object Erich Hoeber E389670 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: Erich Hoeber | Statement: [The Meg, screenwriter, Erich Hoeber]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erich Hoeber
Context triple: [The Meg, screenwriter, Erich Hoeber]
  • A. Erich Hoeber chosen
    Erich Hoeber is an American screenwriter best known for co-writing the action films "Red" and "Battleship."
  • B. Erich Löwenhardt
    Erich Löwenhardt was a German World War I fighter ace credited with over 50 aerial victories and recognized as one of the leading pilots of the Luftstreitkräfte.
  • C. Louis Seelbach
    Louis Seelbach was a prominent Louisville hotelier best known for co-founding and developing the historic Seelbach Hotel in Kentucky.
  • D. Werner von Haeften
    Werner von Haeften was a German army officer and close associate of Claus von Stauffenberg who participated in the failed 20 July 1944 plot to assassinate Adolf Hitler and was executed for his role in the conspiracy.
  • E. Otto Schenk
    Otto Schenk is an Austrian actor, director, and comedian renowned for his work in theater and opera, particularly at the Vienna State Opera and the Metropolitan Opera.
  • 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_69d81c5eaa9c819083b1ff8689179565 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2723461881908376b5509ee0d530 completed April 14, 2026, 11:38 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00679214208190a9ee4cce882f59cb completed May 10, 2026, 11:10 a.m.
Created at: April 9, 2026, 10:16 p.m.