Triple

T2320285
Position Surface form Disambiguated ID Type / Status
Subject Northern Michigan E51163 entity
Predicate hasPart P35 FINISHED
Object Gaylord
Gaylord is a small city in northern Michigan known for its Alpine-themed architecture and outdoor recreation opportunities.
 E256119 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: Gaylord | Statement: [Northern Michigan, hasPart, Gaylord]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gaylord
Context triple: [Northern Michigan, hasPart, Gaylord]
  • A. Gaylord City Elk Park
    Gaylord City Elk Park is a small wildlife viewing area in Gaylord, Michigan, where visitors can observe a managed herd of elk in a natural-like setting.
  • B. Gaylord Entertainment Center
    Gaylord Entertainment Center was a major indoor sports and entertainment arena in Nashville, Tennessee, that served as the longtime home venue for the city’s NHL team before being renamed.
  • C. Milhous
    Milhous is the distinctive middle name of Richard Nixon, the 37th president of the United States.
  • D. Ray Brook
    Ray Brook is a small hamlet in New York’s Adirondack region that serves as an administrative center for several state and environmental agencies.
  • E. Hamner
    Hamner is the surname of Earl Hamner Jr., the American writer and creator best known for the television series "The Waltons."
  • 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: Gaylord
Triple: [Northern Michigan, hasPart, Gaylord]
Generated description
Gaylord is a small city in northern Michigan known for its Alpine-themed architecture and outdoor recreation opportunities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gaylord
Target entity description: Gaylord is a small city in northern Michigan known for its Alpine-themed architecture and outdoor recreation opportunities.
  • A. Gaylord City Elk Park
    Gaylord City Elk Park is a small wildlife viewing area in Gaylord, Michigan, where visitors can observe a managed herd of elk in a natural-like setting.
  • B. Gaylord Entertainment Center
    Gaylord Entertainment Center was a major indoor sports and entertainment arena in Nashville, Tennessee, that served as the longtime home venue for the city’s NHL team before being renamed.
  • C. Milhous
    Milhous is the distinctive middle name of Richard Nixon, the 37th president of the United States.
  • D. Ray Brook
    Ray Brook is a small hamlet in New York’s Adirondack region that serves as an administrative center for several state and environmental agencies.
  • E. Hamner
    Hamner is the surname of Earl Hamner Jr., the American writer and creator best known for the television series "The Waltons."
  • 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_69a88b074b908190ae983dbca7757d88 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc632474c8190972b4611a3a4ff8f completed March 7, 2026, 6:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae896911908190b53954dbf854cc18 completed March 9, 2026, 8:48 a.m.
NEDg Description generation batch_69ae8d2dcc8081908d4274b2287ff2b8 completed March 9, 2026, 9:04 a.m.
NED2 Entity disambiguation (via description) batch_69ae8d786a648190acf0a14e0d4a120c completed March 9, 2026, 9:06 a.m.
Created at: March 4, 2026, 7:49 p.m.