Triple

T8057296
Position Surface form Disambiguated ID Type / Status
Subject Erich Fromm E188032 entity
Predicate employer P7 FINISHED
Object Bennington College E293452 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: Bennington College | Statement: [Erich Fromm, employer, Bennington College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bennington College
Context triple: [Erich Fromm, employer, Bennington College]
  • A. Bennington College chosen
    Bennington College is a small, progressive liberal arts college in Bennington, Vermont, known for its emphasis on the arts, individualized study, and experimental education.
  • B. College of the Atlantic
    College of the Atlantic is a small, environmentally focused liberal arts college in Bar Harbor, Maine, known for its interdisciplinary curriculum centered on human ecology.
  • C. Goddard College
    Goddard College is a progressive, low-residency liberal arts college in Vermont known for its individualized, student-directed education.
  • D. Skidmore College
    Skidmore College is a private liberal arts college known for its strong emphasis on creative thought and interdisciplinary education.
  • E. Milligan College
    Milligan College is a private Christian liberal arts college in Tennessee known for its strong emphasis on faith-based education and service.
  • 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_69ca82b2f68881908c50560697e210da completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3fa3dd2481909e925304fcea2111 completed March 31, 2026, 3:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc93cc0cec8190834e4c24f6d03a99 completed April 1, 2026, 3:41 a.m.
Created at: March 30, 2026, 5:25 p.m.