Triple

T11083914
Position Surface form Disambiguated ID Type / Status
Subject Marilyn Miller E262068 entity
Predicate notableWork P4 FINISHED
Object Sunny E258807 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: Sunny | Statement: [Marilyn Miller, notableWork, Sunny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sunny
Context triple: [Marilyn Miller, notableWork, Sunny]
  • A. Sunny
    Sunny is one of the Obama family’s pet dogs, a female Portuguese Water Dog who lived with them in the White House.
  • B. Sunny chosen
    "Sunny" is a 1925 Broadway musical comedy with music by Jerome Kern that became one of his popular stage successes of the era.
  • C. Sunny
    Sunny Sandler is an American child actress and the daughter of comedian and actor Adam Sandler.
  • D. Sunny
    Sunny is a central character in the crime drama "8 Million Ways to Die," serving as a key figure in the film’s gritty narrative of murder, addiction, and moral ambiguity.
  • E. Sunny
    Sunny is a child prodigy and skilled hacker in the Metal Gear Solid series, known as the adopted daughter of Otacon and the biological daughter of Olga Gurlukovich.
  • 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_69d6aa9983c08190b0ef61603b69feac completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d799c0cc3081908448cfb26c08daf5 completed April 9, 2026, 12:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3e79854c88190bda69cfbe4ae9d1e completed April 18, 2026, 8:20 p.m.
Created at: April 8, 2026, 9:27 p.m.