Triple

T7332083
Position Surface form Disambiguated ID Type / Status
Subject Wesleyan University E169026 entity
Predicate locatedIn P40 FINISHED
Object Middletown, Connecticut E222856 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: Middletown, Connecticut | Statement: [Wesleyan University, locatedIn, Middletown, Connecticut]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Middletown, Connecticut
Context triple: [Wesleyan University, locatedIn, Middletown, Connecticut]
  • A. Middletown
    Middletown is a small historic town located in Frederick County in the northern Shenandoah Valley region of Virginia, United States.
  • B. Middletown
    Middletown is a coastal town on Aquidneck Island in Rhode Island, known for its beaches, historic sites, and proximity to Newport.
  • C. Middletown
    Middletown is one of New Jersey’s oldest and largest suburban communities, known for its historic roots, residential neighborhoods, and proximity to the Jersey Shore.
  • D. Middletown chosen
    Middletown is a city in central Connecticut known as the home of Wesleyan University and its historic downtown along the Connecticut River.
  • E. Middletown, New York
    Middletown, New York is a small city in Orange County that serves as a commercial and residential hub in New York’s Hudson Valley region.
  • 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_69c68a568a6481908f11e20db7bc8446 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f0bf93dc8190931c13865ba827dd completed March 27, 2026, 9:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce38b159d0819087efca6f80797971 completed April 2, 2026, 9:36 a.m.
Created at: March 27, 2026, 3:03 p.m.