Triple

T14880838
Position Surface form Disambiguated ID Type / Status
Subject Alice Cullen E349994 entity
Predicate birthName P65 FINISHED
Object Mary Alice Brandon E435074 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: Mary Alice Brandon | Statement: [Alice Cullen, birthName, Mary Alice Brandon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Alice Brandon
Context triple: [Alice Cullen, birthName, Mary Alice Brandon]
  • A. Mary Richards
    Mary Richards is the independent, career-focused television news producer portrayed by Mary Tyler Moore on the influential 1970s sitcom "The Mary Tyler Moore Show."
  • B. Mary Richards
    Mary Richards was the wife of colonial governor Thomas Hinckley of Plymouth Colony in 17th-century New England.
  • C. Mary Alice chosen
    Mary Alice was an American actress best known for her roles in film, television, and theater, including portraying the Oracle in "The Matrix Revolutions."
  • D. Mary Alice Moore
    Mary Alice Moore was the wife of American actor Broderick Crawford, known for his Academy Award–winning role in "All the King's Men."
  • E. Betsy Brantley
    Betsy Brantley is an American actress known for her work in film, television, and theater, including roles in productions such as "The Princess Bride" and "Deep Impact."
  • 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_69d822ee4f408190b6ac3b2fa434f0df completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded5e622388190b2bf91cd10b9821d completed April 15, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe7e8192548190ad268b5804c97060 completed May 9, 2026, 12:23 a.m.
Created at: April 10, 2026, 1:55 a.m.