Triple

T23486448
Position Surface form Disambiguated ID Type / Status
Subject Bill Campbell E570545 entity
Predicate mentorOf P7251 FINISHED
Object Sheryl Sandberg NE NERFINISHED

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: Sheryl Sandberg | Statement: [Bill Campbell, mentorOf, Sheryl Sandberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sheryl Sandberg
Context triple: [Bill Campbell, mentorOf, Sheryl Sandberg]
  • A. Sheryl Sandberg chosen
    Sheryl Sandberg is an American technology executive, author, and former Chief Operating Officer of Meta (formerly Facebook), widely recognized for her leadership in Silicon Valley and advocacy for women in the workplace.
  • B. Patty McCord
    Patty McCord is a human resources executive and author best known as Netflix’s former Chief Talent Officer and co-creator of its influential “culture deck” on freedom and responsibility.
  • C. Raj K. Nooyi
    Raj K. Nooyi is best known as the husband of former PepsiCo CEO Indra Nooyi and is a management consultant by profession.
  • D. Sue Kanter
    Sue Kanter is known as the wife of American comedy writer, producer, and director Hal Kanter.
  • E. Indra Nooyi
    Indra Nooyi is an Indian-American business executive best known for serving as the influential former CEO and chairperson of PepsiCo.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a754825481909b005ca5654c3159 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:04 p.m.