Triple

T11022731
Position Surface form Disambiguated ID Type / Status
Subject Jeannie Seely E260530 entity
Predicate givenName P17 FINISHED
Object Marilyn
Marilyn is the given first name of American country music singer Jeannie Seely.
 E901517 NE FINISHED

How this triple was built (4 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: Marilyn | Statement: [Jeannie Seely, givenName, Marilyn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marilyn
Context triple: [Jeannie Seely, givenName, Marilyn]
  • A. Marilyn
    A Marilyn is a type of British hill or mountain classified by having a prominence of at least 150 meters, regardless of its absolute height.
  • B. Marlene
    Marlene is a German biographical film directed by Joseph Vilsmaier about the life and career of actress and singer Marlene Dietrich.
  • C. Marlene
    Marlene is an energetic and friendly otter who appears as a main supporting character in the animated series "The Penguins of Madagascar."
  • D. Marilyn Monroe
    Marilyn Monroe was an iconic American actress, model, and sex symbol of the mid-20th century, renowned for her comedic roles, glamorous image, and enduring cultural legacy.
  • E. Gloria
    Gloria is a 1980 American crime drama film written and directed by John Cassavetes, starring Gena Rowlands as a tough ex-mobster’s girlfriend protecting a young boy from gangsters.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Marilyn
Triple: [Jeannie Seely, givenName, Marilyn]
Generated description
Marilyn is the given first name of American country music singer Jeannie Seely.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marilyn
Target entity description: Marilyn is the given first name of American country music singer Jeannie Seely.
  • A. Marilyn
    A Marilyn is a type of British hill or mountain classified by having a prominence of at least 150 meters, regardless of its absolute height.
  • B. Marlene
    Marlene is an energetic and friendly otter who appears as a main supporting character in the animated series "The Penguins of Madagascar."
  • C. Marlene
    Marlene is a German biographical film directed by Joseph Vilsmaier about the life and career of actress and singer Marlene Dietrich.
  • D. Marilyn Monroe
    Marilyn Monroe was an iconic American actress, model, and sex symbol of the mid-20th century, renowned for her comedic roles, glamorous image, and enduring cultural legacy.
  • E. Gloria
    Gloria is an angelic character on the television series "Touched by an Angel," known for assisting Monica and Tess in delivering divine guidance to people in need.
  • F. None of above. chosen

Provenance (5 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797bd88188190a644adc9283cabb8 completed April 9, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3a997d7bc8190982467039e0f5504 completed April 18, 2026, 3:56 p.m.
NEDg Description generation batch_69e3b1dfea348190a61eb19266801ad0 completed April 18, 2026, 4:31 p.m.
NED2 Entity disambiguation (via description) batch_69e3b2c65fa081908038cc2f71e49073 completed April 18, 2026, 4:35 p.m.
Created at: April 8, 2026, 9:25 p.m.