Triple

T3355830
Position Surface form Disambiguated ID Type / Status
Subject Marjorie Merriweather Post E70602 entity
Predicate child P120 FINISHED
Object Dina Merrill E270783 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: Dina Merrill | Statement: [Marjorie Merriweather Post, child, Dina Merrill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dina Merrill
Context triple: [Marjorie Merriweather Post, child, Dina Merrill]
  • A. Dina Merrill chosen
    Dina Merrill was an American actress, heiress, and philanthropist known for her elegant screen presence in mid-20th-century Hollywood films and television.
  • B. Joan Bennett
    Joan Bennett was a prominent American film actress of the 1930s and 1940s, known for her transition from blonde ingenue roles to sultry film noir femme fatales under director Fritz Lang.
  • C. Evelyn Keyes
    Evelyn Keyes was an American film actress best known for her role as Suellen O'Hara in the classic 1939 film "Gone with the Wind."
  • D. Anne Francis
    Anne Francis was an American actress best known for her roles in films like "Forbidden Planet" and the TV series "Honey West," for which she received Emmy and Golden Globe nominations.
  • E. Nancy Richardson
    Nancy Richardson is a film editor best known for her work on movies such as the biographical sports comedy-drama "Fighting with My Family."
  • 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_69ad85a660c48190998489309a3b4869 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb2419a808190a54fc03eeec6e42d completed March 8, 2026, 5:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b65f07e50c8190be1d760f209c4aea completed March 15, 2026, 7:26 a.m.
Created at: March 8, 2026, 3:13 p.m.