Triple

T20302831
Position Surface form Disambiguated ID Type / Status
Subject Belgian railway line 53 E505526 entity
Predicate passesThrough P225 FINISHED
Object Leest
Leest is a village in the municipality of Mechelen in the Belgian province of Antwerp.
E1423272 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: Leest | Statement: [Belgian railway line 53, passesThrough, Leest]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leest
Context triple: [Belgian railway line 53, passesThrough, Leest]
  • A. Lees
    Lees is the surname of Andrea Leeds, an American film actress prominent in the 1930s and 1940s.
  • B. Lees
    Lees is a village in the Metropolitan Borough of Oldham, Greater Manchester, England, historically part of Lancashire.
  • C. Leer
    Leer is a historic town in northwestern Germany known for its maritime heritage and traditional East Frisian culture.
  • D. Léez
    Léez is a river in southwestern France that serves as a tributary within the Gave de Pau river system.
  • E. Leestma
    Leestma is a surname most notably associated with David C. Leestma, an American astronaut and former NASA official.
  • 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: Leest
Triple: [Belgian railway line 53, passesThrough, Leest]
Generated description
Leest is a village in the municipality of Mechelen in the Belgian province of Antwerp.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Leest
Target entity description: Leest is a village in the municipality of Mechelen in the Belgian province of Antwerp.
  • A. Lees
    Lees is the surname of Andrea Leeds, an American film actress prominent in the 1930s and 1940s.
  • B. Lees
    Lees is a village in the Metropolitan Borough of Oldham, Greater Manchester, England, historically part of Lancashire.
  • C. Leer
    Leer is a historic town in northwestern Germany known for its maritime heritage and traditional East Frisian culture.
  • D. Léez
    Léez is a river in southwestern France that serves as a tributary within the Gave de Pau river system.
  • E. Leestma
    Leestma is a surname most notably associated with David C. Leestma, an American astronaut and former NASA official.
  • 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6773e0864819095d272659cd2074d completed April 20, 2026, 6:58 p.m.
NED1 Entity disambiguation (via context triple) batch_6a086119b9808190ba5ebb80b43953d3 completed May 16, 2026, 12:20 p.m.
NEDg Description generation batch_6a0861b954888190a6305aa805aa97ff completed May 16, 2026, 12:23 p.m.
NED2 Entity disambiguation (via description) batch_6a0862237d148190b4e12c878ca9c7a2 completed May 16, 2026, 12:25 p.m.
Created at: April 16, 2026, 11:17 a.m.