Triple

T22447542
Position Surface form Disambiguated ID Type / Status
Subject Millersville University of Pennsylvania E554902 entity
Predicate city P40 FINISHED
Object Millersville 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: Millersville | Statement: [Millersville University of Pennsylvania, city, Millersville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Millersville
Context triple: [Millersville University of Pennsylvania, city, Millersville]
  • A. Millersville, Pennsylvania chosen
    Millersville, Pennsylvania is a small borough best known as the home of Millersville University, located just outside the city of Lancaster.
  • B. Millerstown, Pennsylvania
    Millerstown, Pennsylvania is a small borough in central Pennsylvania known for its rural character and historic charm along the Juniata River.
  • C. Montoursville
    Montoursville is a small borough in north-central Pennsylvania, United States, known for its residential community and proximity to the city of Williamsport.
  • D. Petersville
    Petersville is a small, remote community in Alaska known as a gateway to outdoor recreation and backcountry areas within the Matanuska-Susitna Borough.
  • E. Millersburg
    Millersburg is a small city located in Iowa, United States.
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b48be0481909f4601b732424e5b completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:47 p.m.