Triple

T15466314
Position Surface form Disambiguated ID Type / Status
Subject Bell Cup E372038 entity
Predicate hasCourse P6650 FINISHED
Object Ribbon Road
Ribbon Road is a colorful, candy-themed racetrack featured in the Mario Kart series.
E1164545 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: Ribbon Road | Statement: [Bell Cup, hasCourse, Ribbon Road]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ribbon Road
Context triple: [Bell Cup, hasCourse, Ribbon Road]
  • A. Serpentine Road
    Serpentine Road is a notable roadway running alongside the Serpentine in Hyde Park, central London.
  • B. Five Mile Road
    Five Mile Road is a major east–west thoroughfare in Livonia, Michigan, forming part of the Detroit area's mile road system and serving as a key route for local traffic and commerce.
  • C. Slipe Road
    Slipe Road is a major thoroughfare in Kingston, Jamaica, serving as a key connector through the Half Way Tree area and surrounding districts.
  • D. Calder Highway
    Calder Highway is a major rural highway in Victoria, Australia, linking Melbourne with the northwestern regions of the state, including the city of Mildura.
  • E. Tara Road
    "Tara Road" is a bestselling contemporary novel by Irish author Maeve Binchy that follows the intertwined lives of two women from Dublin and Connecticut who swap houses to escape personal crises.
  • 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: Ribbon Road
Triple: [Bell Cup, hasCourse, Ribbon Road]
Generated description
Ribbon Road is a colorful, candy-themed racetrack featured in the Mario Kart series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ribbon Road
Target entity description: Ribbon Road is a colorful, candy-themed racetrack featured in the Mario Kart series.
  • A. Serpentine Road
    Serpentine Road is a notable roadway running alongside the Serpentine in Hyde Park, central London.
  • B. Five Mile Road
    Five Mile Road is a major east–west thoroughfare in Livonia, Michigan, forming part of the Detroit area's mile road system and serving as a key route for local traffic and commerce.
  • C. Slipe Road
    Slipe Road is a major thoroughfare in Kingston, Jamaica, serving as a key connector through the Half Way Tree area and surrounding districts.
  • D. Calder Highway
    Calder Highway is a major rural highway in Victoria, Australia, linking Melbourne with the northwestern regions of the state, including the city of Mildura.
  • E. Tara Road
    "Tara Road" is a bestselling contemporary novel by Irish author Maeve Binchy that follows the intertwined lives of two women from Dublin and Connecticut who swap houses to escape personal crises.
  • 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_69d85cc8bd308190886949510b42e764 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f680cec8190836a5ec841dee224 completed April 16, 2026, 1:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c3293dc819097f9e56963c333ee completed May 9, 2026, 3:01 p.m.
NEDg Description generation batch_69ff4e9abb548190972a230bffb2616c completed May 9, 2026, 3:11 p.m.
NED2 Entity disambiguation (via description) batch_69ff4ef514308190a95cb0163717a6b9 completed May 9, 2026, 3:12 p.m.
Created at: April 10, 2026, 3:33 a.m.