Triple

T15842185
Position Surface form Disambiguated ID Type / Status
Subject Spa 24 Hours E384125 entity
Predicate hasCorner P42380 FINISHED
Object La Source
La Source is a well-known high-speed corner at the Circuit de Spa-Francorchamps, famous as the tight hairpin that opens a lap of the Belgian Grand Prix and Spa 24 Hours.
 E1180572 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: La Source | Statement: [Spa 24 Hours, hasCorner, La Source]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: La Source
Context triple: [Spa 24 Hours, hasCorner, La Source]
  • A. La Source
    La Source is the original French title of the 1960 Swedish film "The Virgin Spring," directed by Ingmar Bergman.
  • B. La Source
    La Source is a popular surf break near Taghazout, Morocco, known for its consistent waves and scenic Atlantic coastline.
  • C. La source
    La source is a 19th-century ballet composed by Léo Delibes (with contributions by Ludwig Minkus), known for its lyrical melodies and place in the Romantic ballet repertoire.
  • D. Cerca-la-Source
    Cerca-la-Source is a commune and town in Haiti located within the country's Centre Department.
  • E. La Source depot
    La Source depot is a maintenance and storage facility serving the Orléans tramway network in Orléans, France.
  • 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: La Source
Triple: [Spa 24 Hours, hasCorner, La Source]
Generated description
La Source is a well-known high-speed corner at the Circuit de Spa-Francorchamps, famous as the tight hairpin that opens a lap of the Belgian Grand Prix and Spa 24 Hours.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: La Source
Target entity description: La Source is a well-known high-speed corner at the Circuit de Spa-Francorchamps, famous as the tight hairpin that opens a lap of the Belgian Grand Prix and Spa 24 Hours.
  • A. La Source
    La Source is the original French title of the 1960 Swedish film "The Virgin Spring," directed by Ingmar Bergman.
  • B. La Source
    La Source is a popular surf break near Taghazout, Morocco, known for its consistent waves and scenic Atlantic coastline.
  • C. La source
    La source is a 19th-century ballet composed by Léo Delibes (with contributions by Ludwig Minkus), known for its lyrical melodies and place in the Romantic ballet repertoire.
  • D. Cerca-la-Source
    Cerca-la-Source is a commune and town in Haiti located within the country's Centre Department.
  • E. La Source depot
    La Source depot is a maintenance and storage facility serving the Orléans tramway network in Orléans, France.
  • 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_69d86da34c888190976e06c4019d415a completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e142e88ff08190a1035269e8fdaa6a completed April 16, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa13eab4881908794104508ba53af completed May 9, 2026, 9:03 p.m.
NEDg Description generation batch_69ffa527af048190b1f87d85e50bf254 completed May 9, 2026, 9:20 p.m.
NED2 Entity disambiguation (via description) batch_69ffa5df00e481909e203e78940395ed completed May 9, 2026, 9:23 p.m.
Created at: April 10, 2026, 4:50 a.m.