Triple

T19388792
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth McCord E485005 entity
Predicate hasAdvisor P25349 FINISHED
Object Matt Mahoney 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: Matt Mahoney | Statement: [Elizabeth McCord, hasAdvisor, Matt Mahoney]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matt Mahoney
Context triple: [Elizabeth McCord, hasAdvisor, Matt Mahoney]
  • A. Matt Mahoney chosen
    Matt Mahoney is a fictional character from the political drama television series "Madame Secretary," involved in the professional and personal world surrounding the U.S. Secretary of State.
  • B. Richard Socher
    Richard Socher is a prominent computer scientist and entrepreneur known for his influential work in natural language processing and deep learning, including serving as Chief Scientist at Salesforce and founding the AI company You.com.
  • C. Max Perlich
    Max Perlich is an American character actor known for his offbeat, often quirky supporting roles in independent films and television series since the late 1980s.
  • D. Martin Hinton
    Martin Hinton is a notable individual recognized for sharing the surname associated with the Hinton family name.
  • E. Christopher B. Roberts
    Christopher B. Roberts is an American academic and engineer who serves as the president of Auburn University.
  • 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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61b425e848190ab5ae8ae0a034fe2 completed April 20, 2026, 12:25 p.m.
Created at: April 10, 2026, 1:36 p.m.