Triple

T20302458
Position Surface form Disambiguated ID Type / Status
Subject Arrondissement of Dendermonde E505516 entity
Predicate containsMunicipality P852 FINISHED
Object Laarne
Laarne is a municipality in East Flanders, Belgium, known for its historic medieval castle and rural character near the city of Ghent.
E1468882 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: Laarne | Statement: [Arrondissement of Dendermonde, containsMunicipality, Laarne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laarne
Context triple: [Arrondissement of Dendermonde, containsMunicipality, Laarne]
  • A. Kauriala
    Kauriala is an alternative name for the Ghaghara, a major Himalayan river that flows through Nepal and northern India before joining the Ganges.
  • B. Kerava
    Kerava is a small city in southern Finland known as a commuter town within the Greater Helsinki region.
  • C. Lappeenranta
    Lappeenranta is a city in southeastern Finland near the Russian border, known for its lakeside location on Saimaa and its role as a regional commercial and educational center.
  • D. Raseborg
    Raseborg is a municipality and historic coastal town in southern Finland known for its medieval castle ruins and Swedish-speaking cultural heritage.
  • E. Rieste
    Rieste is a small municipality in Lower Saxony, Germany, situated within the Osnabrück district.
  • 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: Laarne
Triple: [Arrondissement of Dendermonde, containsMunicipality, Laarne]
Generated description
Laarne is a municipality in East Flanders, Belgium, known for its historic medieval castle and rural character near the city of Ghent.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Laarne
Target entity description: Laarne is a municipality in East Flanders, Belgium, known for its historic medieval castle and rural character near the city of Ghent.
  • A. Kauriala
    Kauriala is an alternative name for the Ghaghara, a major Himalayan river that flows through Nepal and northern India before joining the Ganges.
  • B. Kerava
    Kerava is a small city in southern Finland known as a commuter town within the Greater Helsinki region.
  • C. Lappeenranta
    Lappeenranta is a city in southeastern Finland near the Russian border, known for its lakeside location on Saimaa and its role as a regional commercial and educational center.
  • D. Raseborg
    Raseborg is a municipality and historic coastal town in southern Finland known for its medieval castle ruins and Swedish-speaking cultural heritage.
  • E. Rieste
    Rieste is a small municipality in Lower Saxony, Germany, situated within the Osnabrück district.
  • 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_69e6770d82b48190b21ce7c52ec6d5a0 completed April 20, 2026, 6:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a096da3b8e88190bae1daccb216d35a completed May 17, 2026, 7:26 a.m.
NEDg Description generation batch_6a096e80955c819080873bc728d9ab5d completed May 17, 2026, 7:30 a.m.
NED2 Entity disambiguation (via description) batch_6a096f5e96cc8190b3be5a773868bd32 completed May 17, 2026, 7:33 a.m.
Created at: April 16, 2026, 11:17 a.m.