Triple

T10346183
Position Surface form Disambiguated ID Type / Status
Subject Lehigh County, Pennsylvania E243751 entity
Predicate contains P35 FINISHED
Object Cedar Crest College E807884 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: Cedar Crest College | Statement: [Lehigh County, Pennsylvania, contains, Cedar Crest College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cedar Crest College
Context triple: [Lehigh County, Pennsylvania, contains, Cedar Crest College]
  • A. Cedar Crest College chosen
    Cedar Crest College is a private liberal arts women's college located in Allentown, Pennsylvania.
  • B. Cedar Crest
    Cedar Crest is the official residence of the Governor of Kansas, located on a hill overlooking the Kansas River in Topeka.
  • C. Rosemont College
    Rosemont College is a small private liberal arts college located in the Philadelphia Main Line suburbs of Pennsylvania.
  • D. Cabrini University
    Cabrini University is a private Catholic liberal arts university located in Radnor, Pennsylvania, known for its emphasis on social justice and community engagement.
  • E. Fairmount College
    Fairmount College was the original private liberal arts institution that later evolved into Wichita State University in Wichita, Kansas.
  • 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_69d381b22b8c8190aaed476be5f872a9 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e923e3d08190971073ce41ff860f completed April 7, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7507f708c8190b8cf684704a6e47d completed April 9, 2026, 7:08 a.m.
Created at: April 6, 2026, 11:56 a.m.