Triple

T16865502
Position Surface form Disambiguated ID Type / Status
Subject Mabel Loomis Todd E410024 entity
Predicate residence P75 FINISHED
Object Amherst, Massachusetts E25328 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: Amherst, Massachusetts | Statement: [Mabel Loomis Todd, residence, Amherst, Massachusetts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amherst, Massachusetts
Context triple: [Mabel Loomis Todd, residence, Amherst, Massachusetts]
  • A. Amherst, Massachusetts chosen
    Amherst, Massachusetts is a New England college town best known as the home of the University of Massachusetts Amherst and Amherst College.
  • B. Amherst
    Amherst is an English surname historically associated with the British aristocratic Amherst family, including military commander Jeffery Amherst, 1st Baron Amherst.
  • C. Amherst
    Amherst is a town in northwestern Nova Scotia, Canada, known historically as a regional industrial and transportation hub.
  • D. Amherst
    Amherst is a small unincorporated community located within Sedgwick County in the U.S. state of Kansas.
  • E. Wellesley, Massachusetts
    Wellesley, Massachusetts is an affluent suburban town west of Boston known for its highly ranked public schools and as the home of Wellesley College.
  • 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_69d88395e6c88190b22730f335107c14 completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b506dd1c81909ab8006b6a1e2b7a completed April 18, 2026, 4:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00cfc531c881908a33de8b491842ca completed May 10, 2026, 6:34 p.m.
Created at: April 10, 2026, 5:24 a.m.