Triple

T6223259
Position Surface form Disambiguated ID Type / Status
Subject William G. Morgan E139167 entity
Predicate familyName P18 FINISHED
Object Morgan E137073 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: Morgan | Statement: [William G. Morgan, familyName, Morgan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Morgan
Context triple: [William G. Morgan, familyName, Morgan]
  • A. Morgan
    Morgan is the party that successfully defended the constitutionality of a key provision of the Voting Rights Act in the landmark U.S. Supreme Court case Katzenbach v. Morgan.
  • B. Morgan chosen
    Morgan is a prominent American banking and finance family name most famously associated with financier J. P. Morgan and the powerful House of Morgan banking dynasty.
  • C. Morgan
    Morgan is the middle name of the renowned English novelist and essayist E. M. Forster.
  • D. Morgan
    Morgan is a 2016 science fiction horror film about a genetically engineered human hybrid whose violent behavior leads to a crisis among the scientists who created her.
  • E. Morgan
    Morgan is a Chicago 'L' rapid transit station on the Near West Side serving the city's Pink and Green Lines.
  • 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_69c008aecb0c81909984b48f733ce8ae completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062c06c7881909999ba44aa4a23f9 completed March 22, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20dcc5e788190a510cac6bbad4830 completed March 24, 2026, 4:06 a.m.
Created at: March 22, 2026, 4:22 p.m.