Triple

T15567
Position Surface form Disambiguated ID Type / Status
Subject Harvard Yard E310 entity
Predicate contains P35 FINISHED
Object John Harvard statue E1140 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: John Harvard statue | Statement: [Harvard Yard, contains, John Harvard statue]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Harvard statue
Context triple: [Harvard Yard, contains, John Harvard statue]
  • A. John Harvard statue chosen
    The John Harvard statue is a famous bronze monument in Harvard Yard that has become an iconic symbol of Harvard University and a popular tourist attraction.
  • B. John Harvard
    John Harvard was a 17th-century English clergyman and benefactor whose substantial bequest helped establish the institution that became Harvard University.
  • C. Washington Monument
    The Washington Monument is a towering white marble obelisk on the National Mall that honors George Washington, the first president of the United States.
  • D. Harvard Yard
    Harvard Yard is the historic central area of Harvard University’s campus in Cambridge, Massachusetts, known for its iconic brick buildings, freshman dormitories, and academic landmarks.
  • E. Harvard Library
    Harvard Library is the extensive academic library system of Harvard University, recognized as one of the largest and most comprehensive research library networks in the world.
  • 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_69a23d7ad88c8190bffe8ab091d86642 completed Feb. 28, 2026, 12:57 a.m.
NER Named-entity recognition batch_69a2400257208190b3cd87ad2a06c18f completed Feb. 28, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69a248e572f08190b52158e063a066bf completed Feb. 28, 2026, 1:46 a.m.
Created at: Feb. 28, 2026, 1:02 a.m.