Triple

T15879276
Position Surface form Disambiguated ID Type / Status
Subject Francis Phillip Wuppermann E385030 entity
Predicate alsoKnownAs P39 FINISHED
Object Frank Morgan E58209 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: Frank Morgan | Statement: [Francis Phillip Wuppermann, alsoKnownAs, Frank Morgan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Morgan
Context triple: [Francis Phillip Wuppermann, alsoKnownAs, Frank Morgan]
  • A. Frank Morgan chosen
    Frank Morgan was an American character actor best known for playing multiple roles, including the title character, in the classic 1939 film "The Wizard of Oz."
  • B. Ernest Stillman
    Ernest Stillman was an American physician and conservationist best known for establishing Black Rock Forest in New York as a protected research and educational preserve.
  • C. William Eddins McMath
    William Eddins McMath was an American individual known primarily through genealogical records as the husband of Lela Emogene Owens McMath.
  • D. Thomas Graham Kahn
    Thomas Graham Kahn is a member of the Kahn family associated with renowned value investor Irving Kahn.
  • E. Charles Aubrey Smith
    Charles Aubrey Smith was an English cricketer-turned-character actor best known for playing dignified, often aristocratic English gentlemen in early Hollywood films.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155ff96588190b8fca1c3bf4a39a2 completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb043b6d48190bf9a36a3e00403c0 completed May 9, 2026, 10:08 p.m.
Created at: April 10, 2026, 4:51 a.m.