Triple

T20603045
Position Surface form Disambiguated ID Type / Status
Subject Belgian railway line 52 E506230 entity
Predicate connects P390 FINISHED
Object Puurs
Puurs is a municipality in the Belgian province of Antwerp, known for its brewing industry and location between Antwerp and Brussels.
 E1439636 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: Puurs | Statement: [Belgian railway line 52, connects, Puurs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Puurs
Context triple: [Belgian railway line 52, connects, Puurs]
  • A. Woensel
    Woensel is a large residential district in the northern part of the Dutch city of Eindhoven, known for its diverse population and extensive post-war housing.
  • B. Hoornaar
    Hoornaar is a village in the Dutch province of South Holland, known for its rural character and traditional polder landscape.
  • C. Zwartsluis
    Zwartsluis is a small Dutch town in the province of Overijssel, known for its waterways, historic harbor, and role as a regional boating and water sports hub.
  • D. Poulus
    Poulus is a personal name variant derived from the given name Poul.
  • E. Conijn
    Conijn is a Dutch surname of likely patronymic or toponymic origin borne by individuals such as Lucas Conijn.
  • 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: Puurs
Triple: [Belgian railway line 52, connects, Puurs]
Generated description
Puurs is a municipality in the Belgian province of Antwerp, known for its brewing industry and location between Antwerp and Brussels.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Puurs
Target entity description: Puurs is a municipality in the Belgian province of Antwerp, known for its brewing industry and location between Antwerp and Brussels.
  • A. Woensel
    Woensel is a large residential district in the northern part of the Dutch city of Eindhoven, known for its diverse population and extensive post-war housing.
  • B. Hoornaar
    Hoornaar is a village in the Dutch province of South Holland, known for its rural character and traditional polder landscape.
  • C. Zwartsluis
    Zwartsluis is a small Dutch town in the province of Overijssel, known for its waterways, historic harbor, and role as a regional boating and water sports hub.
  • D. Poulus
    Poulus is a personal name variant derived from the given name Poul.
  • E. Conijn
    Conijn is a Dutch surname of likely patronymic or toponymic origin borne by individuals such as Lucas Conijn.
  • 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_69e0b4bb2b4081908fa4a72444120f35 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aa22663881909a8d4644e1c48dc2 completed April 20, 2026, 10:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08b3f35cb08190a7cdc354534fba1c completed May 16, 2026, 6:14 p.m.
NEDg Description generation batch_6a08b4c5946081909ac59ed47f3ba909 completed May 16, 2026, 6:17 p.m.
NED2 Entity disambiguation (via description) batch_6a08b53450a481909133bd18c34dc78c completed May 16, 2026, 6:19 p.m.
Created at: April 16, 2026, 11:41 a.m.