Triple

T18963440
Position Surface form Disambiguated ID Type / Status
Subject The Killer Angels E463968 entity
Predicate author P4 FINISHED
Object Michael Shaara 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: Michael Shaara | Statement: [The Killer Angels, author, Michael Shaara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Shaara
Context triple: [The Killer Angels, author, Michael Shaara]
  • A. Michael Shaara chosen
    Michael Shaara was an American author best known for his Pulitzer Prize–winning Civil War novel "The Killer Angels," which inspired the film "Gettysburg."
  • B. Arthur T. Horman
    Arthur T. Horman was an American screenwriter active during Hollywood’s classic era, known for crafting scripts for adventure and war films.
  • C. Walter Lord
    Walter Lord was an American historian and author best known for his meticulously researched narrative account of the Titanic disaster, "A Night to Remember."
  • D. Bruce Catton
    Bruce Catton was an American historian and Pulitzer Prize–winning author best known for his popular and influential books on the American Civil War.
  • E. Stephen E. Ambrose
    Stephen E. Ambrose was an American historian and biographer best known for his popular works on World War II and the U.S. presidency.
  • 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_69d8dcffc278819086792a4ebfddfafa completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d5d420f481909aa22a0d22ac4af1 completed April 20, 2026, 7:29 a.m.
Created at: April 10, 2026, noon