Triple

T13968950
Position Surface form Disambiguated ID Type / Status
Subject Merit Network E336000 entity
Predicate operated P1688 FINISHED
Object MichNet
MichNet was an early academic and research computer network in Michigan that provided statewide connectivity for universities and institutions.
E1072203 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: MichNet | Statement: [Merit Network, operated, MichNet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MichNet
Context triple: [Merit Network, operated, MichNet]
  • A. MILNET
    MILNET was a U.S. military computer network that formed the unclassified, operational branch of the early Defense Data Network, separate from research-focused ARPANET.
  • B. NETCOM
    NETCOM is a major U.S. Army command responsible for operating, securing, and managing the Army’s global enterprise network and communications infrastructure.
  • C. MCIP
    MCIP is the stock ticker symbol for MCI Inc., a former major American telecommunications company known for providing long-distance and internet services.
  • D. NETWORK
    NETWORK is the radio callsign used by Network Aviation, an Australian regional airline operating charter and scheduled services.
  • E. NET
    NET is the stock ticker symbol for Cloudflare, Inc., a company that provides cloud-based web infrastructure and security services.
  • 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: MichNet
Triple: [Merit Network, operated, MichNet]
Generated description
MichNet was an early academic and research computer network in Michigan that provided statewide connectivity for universities and institutions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MichNet
Target entity description: MichNet was an early academic and research computer network in Michigan that provided statewide connectivity for universities and institutions.
  • A. MILNET
    MILNET was a U.S. military computer network that formed the unclassified, operational branch of the early Defense Data Network, separate from research-focused ARPANET.
  • B. NETCOM
    NETCOM is a major U.S. Army command responsible for operating, securing, and managing the Army’s global enterprise network and communications infrastructure.
  • C. MCIP
    MCIP is the stock ticker symbol for MCI Inc., a former major American telecommunications company known for providing long-distance and internet services.
  • D. NETWORK
    NETWORK is the radio callsign used by Network Aviation, an Australian regional airline operating charter and scheduled services.
  • E. NET
    NET is the stock ticker symbol for Cloudflare, Inc., a company that provides cloud-based web infrastructure and security services.
  • 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_69d81c61f3508190aaf2ca0dc0002c59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e8daeac8190aadd4b3b60222482 completed April 14, 2026, 12:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fba1da70588190a6c9a3895d92be5b completed May 6, 2026, 8:17 p.m.
NEDg Description generation batch_69fba74a96b08190a08c51c231e49e5d completed May 6, 2026, 8:40 p.m.
NED2 Entity disambiguation (via description) batch_69fba8585fb08190998d6a005dc0bd31 completed May 6, 2026, 8:45 p.m.
Created at: April 9, 2026, 10:18 p.m.