Triple

T4107858
Position Surface form Disambiguated ID Type / Status
Subject Eastern Michigan University E88498 entity
Predicate abbreviation P43 FINISHED
Object EMU
EMU is a public university located in Ypsilanti, Michigan, known for its diverse academic programs and strong emphasis on education, business, and health-related fields.
 E413940 NE FINISHED

How this triple was built (4 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: EMU | Statement: [Eastern Michigan University, abbreviation, EMU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EMU
Context triple: [Eastern Michigan University, abbreviation, EMU]
  • A. EMU
    EMU is the European Union’s framework for coordinating economic policy and managing the single currency, the euro, among participating member states.
  • B. EMU
    EMU (Electric Multiple Unit) is a self-propelled train consisting of multiple carriages powered by electricity, commonly used for passenger rail services.
  • C. EMD
    EMD is the commonly used abbreviation for the Engineering Management Division, a professional group focused on the practice and advancement of engineering management.
  • D. EMD
    EMD is the vehicle registration code assigned to the German town of Emden.
  • E. EA
    EA is the commonly used abbreviation for the Environment Agency, the public body responsible for environmental protection and regulation in England.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: EMU
Triple: [Eastern Michigan University, abbreviation, EMU]
Generated description
EMU is a public university located in Ypsilanti, Michigan, known for its diverse academic programs and strong emphasis on education, business, and health-related fields.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EMU
Target entity description: EMU is a public university located in Ypsilanti, Michigan, known for its diverse academic programs and strong emphasis on education, business, and health-related fields.
  • A. EMU
    EMU is the European Union’s framework for coordinating economic policy and managing the single currency, the euro, among participating member states.
  • B. EMU
    EMU (Electric Multiple Unit) is a self-propelled train consisting of multiple carriages powered by electricity, commonly used for passenger rail services.
  • C. EMD
    EMD is the commonly used abbreviation for the Engineering Management Division, a professional group focused on the practice and advancement of engineering management.
  • D. EMD
    EMD is the vehicle registration code assigned to the German town of Emden.
  • E. EA
    EA is the commonly used abbreviation for the Environment Agency, the public body responsible for environmental protection and regulation in England.
  • F. None of above. chosen

Provenance (5 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_69aed9484fb881909146f4c772ad277c completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af019e23c481909578eba1c9270282 completed March 9, 2026, 5:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69b56b8240248190afd026a450958d4c completed March 14, 2026, 2:06 p.m.
NEDg Description generation batch_69b56cbf12348190836f79e509468a3d completed March 14, 2026, 2:12 p.m.
NED2 Entity disambiguation (via description) batch_69b570aef9008190bf8ef2deb00178ae completed March 14, 2026, 2:29 p.m.
Created at: March 9, 2026, 3:40 p.m.