Triple

T16296510
Position Surface form Disambiguated ID Type / Status
Subject Leave Her to Heaven E395660 entity
Predicate starring P1507 FINISHED
Object Mary Philips E86777 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 Philips | Statement: [Leave Her to Heaven, starring, Mary Philips]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Philips
Context triple: [Leave Her to Heaven, starring, Mary Philips]
  • A. Mary Philips chosen
    Mary Philips was an American stage and film actress of the early 20th century, known for her Broadway work and early marriage to Humphrey Bogart.
  • B. Mary Desha
    Mary Desha was an American educator and civic leader best known as one of the four co-founders of the patriotic lineage organization Daughters of the American Revolution.
  • C. Mary Viola
    Mary Viola is a film producer known for her work on projects such as the sports drama "We Are Marshall."
  • D. Mary Bland
    Mary Bland was a member of the prominent Virginia Bland family and the mother of Revolutionary-era planter and politician Henry Lee II.
  • E. Susanna Drake
    Susanna Drake is the central female protagonist of the novel and film "Raintree County," whose complex relationships and personal struggles drive much of the story’s emotional and dramatic tension.
  • 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_69d87f23bb088190a16fbb91a1957ea5 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e25e2dcdac819083918f0964dd5666 completed April 17, 2026, 4:22 p.m.
NED1 Entity disambiguation (via context triple) batch_6a001f9b42248190a3c8c2647a42aeb9 completed May 10, 2026, 6:03 a.m.
Created at: April 10, 2026, 5:06 a.m.