Triple

T22699740
Position Surface form Disambiguated ID Type / Status
Subject UM System E561282 entity
Predicate shortName P43 FINISHED
Object UM System 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: UM System | Statement: [UM System, shortName, UM System]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UM System
Context triple: [UM System, shortName, UM System]
  • A. UM System chosen
    UM System is the multi-campus public university system that oversees the University of Missouri’s constituent institutions and related operations across the state.
  • B. University of Texas System
    The University of Texas System is a large public university system in Texas comprising multiple academic and health institutions, including flagship campuses like the University of Texas at Austin.
  • C. University of Alabama System
    The University of Alabama System is a public university system in the U.S. state of Alabama that oversees multiple campuses and associated institutions, including the flagship University of Alabama.
  • D. UAB
    UAB is the abbreviated name of the Universitaire Associatie Brussel, a higher education association based in Brussels, Belgium.
  • E. UAB
    UAB is a major public research university located near Barcelona, Spain, known for its strong international orientation and wide range of academic programs.
  • 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_69e2454e615481909c177440be559d2c completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178c944748190a0712983f7059114 completed April 29, 2026, 3:19 a.m.
Created at: April 17, 2026, 3:15 p.m.