Triple

T18281285
Position Surface form Disambiguated ID Type / Status
Subject PMAC E437868 entity
Predicate relatedTo P37 FINISHED
Object GMAC 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: GMAC | Statement: [PMAC, relatedTo, GMAC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GMAC
Context triple: [PMAC, relatedTo, GMAC]
  • A. American College Testing
    American College Testing (ACT) is a standardized college admissions exam in the United States that assesses high school students' readiness for postsecondary education.
  • B. GMAT chosen
    The GMAT is a standardized, computer-adaptive exam used worldwide to assess analytical, quantitative, verbal, and writing skills for admission to graduate business programs.
  • C. Kaplan
    Kaplan is a surname most notably associated with Mordecai Kaplan, an influential 20th-century rabbi and theologian who founded Reconstructionist Judaism.
  • D. Kaplan
    Kaplan is a type of adjustable-blade water turbine commonly used in low-head hydroelectric power plants to efficiently generate electricity from flowing water.
  • E. College Board
    The College Board is a U.S.-based nonprofit organization best known for administering standardized tests such as the SAT and Advanced Placement (AP) exams used in college admissions and credit.
  • 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50056ea0481908d66bf263ac80c75 completed April 19, 2026, 4:18 p.m.
Created at: April 10, 2026, 10:35 a.m.