Triple

T3884005
Position Surface form Disambiguated ID Type / Status
Subject How to Marry a Millionaire E92894 entity
Predicate starring P1507 FINISHED
Object Rory Calhoun E226055 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: Rory Calhoun | Statement: [How to Marry a Millionaire, starring, Rory Calhoun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rory Calhoun
Context triple: [How to Marry a Millionaire, starring, Rory Calhoun]
  • A. Rory Calhoun chosen
    Rory Calhoun was an American film and television actor best known for his roles in Westerns during the 1950s and 1960s.
  • B. Biff Brannon
    Biff Brannon is a thoughtful, observant café owner in Carson McCullers’ novel "The Heart Is a Lonely Hunter," known for his quiet compassion and reflective nature.
  • C. Bret Maverick
    Bret Maverick is a charming, quick-witted professional gambler and con man from the classic Western television series "Maverick," famously portrayed by James Garner.
  • D. Matt Ross
    Matt Ross is an American actor and filmmaker known for roles in projects like "Big Love" and for directing the acclaimed film "Captain Fantastic."
  • E. Roy Rogers Jr.
    Roy Rogers Jr. is the son of legendary American cowboy actor and singer Roy Rogers, known for preserving and promoting his parents’ Western entertainment legacy.
  • 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_69aed9697de0819087c2559295ff3d12 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeec9029908190a7b36a3827734db1 completed March 9, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5125bee048190ba7553797e9fd254 completed March 14, 2026, 7:46 a.m.
Created at: March 9, 2026, 3:20 p.m.