Triple

T9731285
Position Surface form Disambiguated ID Type / Status
Subject Marjorie Frost E235747 entity
Predicate sibling P363 FINISHED
Object Irma Frost E181857 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: Irma Frost | Statement: [Marjorie Frost, sibling, Irma Frost]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Irma Frost
Context triple: [Marjorie Frost, sibling, Irma Frost]
  • A. Irma Frost chosen
    Irma Frost was one of the daughters of renowned American poet Robert Frost.
  • B. Maxine Roby
    Maxine Roby is a central forensic crime lab leader in the television series "CSI: Vegas," known for her sharp investigative skills and authoritative presence.
  • C. Edna Mae McCauley
    Edna Mae McCauley is the central character in the 1980 drama film "Resurrection," a woman who miraculously survives a near-fatal accident and discovers she has the power to heal others.
  • D. Betty Jean Newsome
    Betty Jean Newsome was an American songwriter best known for co-writing James Brown’s classic soul ballad “It’s a Man’s Man’s Man’s World.”
  • E. Marie Tillman
    Marie Tillman is an American philanthropist and founder of the Pat Tillman Foundation, established to honor the legacy of her late husband, NFL player and Army Ranger Pat Tillman, by supporting military veterans and their families through educational scholarships.
  • 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_69ca84d0fad481909cdd45aa77416c48 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9eb2373c81909139c7a2ff2aa541 completed April 1, 2026, 10:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1afba5ec081908044a4aefdc6f9ee completed April 5, 2026, 12:41 a.m.
Created at: March 30, 2026, 8:21 p.m.