Triple

T19808713
Position Surface form Disambiguated ID Type / Status
Subject Morgan Lewis E475883 entity
Predicate educatedAt P5 FINISHED
Object King's College 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: King's College | Statement: [Morgan Lewis, educatedAt, King's College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: King's College
Context triple: [Morgan Lewis, educatedAt, King's College]
  • A. King's College
    King's College is the historic institution in New York City that later became Columbia University, known as one of the oldest and most prestigious universities in the United States.
  • B. King's College
    King's College is a Catholic liberal arts college located in Wilkes-Barre, Pennsylvania.
  • C. King’s College
    King’s College is a historic constituent college of the University of Aberdeen, renowned for its medieval architecture and central role in the university’s early development.
  • D. Queen’s College, London
    Queen’s College, London is a historic independent day school for girls in London, known as one of the first institutions in the UK to offer serious academic education to women.
  • E. King’s College, Cambridge
    King’s College, Cambridge is one of the constituent colleges of the University of Cambridge, renowned for its historic chapel, choral tradition, and riverside setting.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65429fec8819091e20908101b50eb completed April 20, 2026, 4:28 p.m.
Created at: April 10, 2026, 1:50 p.m.