Triple

T15952968
Position Surface form Disambiguated ID Type / Status
Subject Circuit de Spa-Francorchamps E386861 entity
Predicate hasCorner P42380 FINISHED
Object Pouhon
Pouhon is a fast, double-apex left-hand corner at the Spa-Francorchamps racing circuit, known for its high-speed challenge and demanding lateral grip.
 E1186138 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: Pouhon | Statement: [Circuit de Spa-Francorchamps, hasCorner, Pouhon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pouhon
Context triple: [Circuit de Spa-Francorchamps, hasCorner, Pouhon]
  • A. Piti
    Piti is a coastal village and port area on the western shore of Guam, known for its harbor facilities and proximity to Apra Harbor.
  • B. Paroi
    Paroi is a state constituency in Negeri Sembilan, Malaysia, represented in the Negeri Sembilan State Legislative Assembly.
  • C. Puyuma
    Puyuma are an indigenous Austronesian ethnic group of southeastern Taiwan known for their distinct language, matrilineal social structure, and rich ceremonial traditions.
  • D. Mounana
    Mounana is a town in southeastern Gabon known historically for its uranium mining activities.
  • E. Pounawea
    Pounawea is a small coastal settlement in New Zealand’s South Island, known for its scenic estuary setting and access to the Catlins region’s natural attractions.
  • 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: Pouhon
Triple: [Circuit de Spa-Francorchamps, hasCorner, Pouhon]
Generated description
Pouhon is a fast, double-apex left-hand corner at the Spa-Francorchamps racing circuit, known for its high-speed challenge and demanding lateral grip.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pouhon
Target entity description: Pouhon is a fast, double-apex left-hand corner at the Spa-Francorchamps racing circuit, known for its high-speed challenge and demanding lateral grip.
  • A. Piti
    Piti is a coastal village and port area on the western shore of Guam, known for its harbor facilities and proximity to Apra Harbor.
  • B. Paroi
    Paroi is a state constituency in Negeri Sembilan, Malaysia, represented in the Negeri Sembilan State Legislative Assembly.
  • C. Puyuma
    Puyuma are an indigenous Austronesian ethnic group of southeastern Taiwan known for their distinct language, matrilineal social structure, and rich ceremonial traditions.
  • D. Mounana
    Mounana is a town in southeastern Gabon known historically for its uranium mining activities.
  • E. Pounawea
    Pounawea is a small coastal settlement in New Zealand’s South Island, known for its scenic estuary setting and access to the Catlins region’s natural attractions.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156f687dc81908d4afd43ac0b2c8e completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe7ab070819090232efdeecdd5fb completed May 9, 2026, 11:08 p.m.
NEDg Description generation batch_69ffbf61b2ec81909c0f32613bb91a82 completed May 9, 2026, 11:12 p.m.
NED2 Entity disambiguation (via description) batch_69ffbfddd0348190baab794f613c71bf completed May 9, 2026, 11:14 p.m.
Created at: April 10, 2026, 4:53 a.m.