Triple

T15968314
Position Surface form Disambiguated ID Type / Status
Subject Borgloon E387254 entity
Predicate locatedIn P40 FINISHED
Object Haspengouw
Haspengouw is a fertile region in eastern Belgium known for its rolling hills, orchards, and extensive fruit cultivation, especially apples and pears.
E1189544 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: Haspengouw | Statement: [Borgloon, locatedIn, Haspengouw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haspengouw
Context triple: [Borgloon, locatedIn, Haspengouw]
  • A. Beaufays
    Beaufays is a village in the municipality of Chaudfontaine in the province of Liège, Belgium.
  • B. Tatihou
    Tatihou is a small French island off the coast of Normandy known for its historic Vauban fortifications, maritime museum, and rich coastal birdlife.
  • C. Donges
    Donges is a commune in western France’s Loire-Atlantique department, known for its major oil refinery and industrial port facilities along the Loire River.
  • D. Lantheuil
    Lantheuil is a small commune in the Calvados department of the Normandy region in northwestern France.
  • E. Wattrelos
    Wattrelos is a commune in northern France near the Belgian border, known historically for its textile industry and cross-border cultural ties.
  • 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: Haspengouw
Triple: [Borgloon, locatedIn, Haspengouw]
Generated description
Haspengouw is a fertile region in eastern Belgium known for its rolling hills, orchards, and extensive fruit cultivation, especially apples and pears.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Haspengouw
Target entity description: Haspengouw is a fertile region in eastern Belgium known for its rolling hills, orchards, and extensive fruit cultivation, especially apples and pears.
  • A. Beaufays
    Beaufays is a village in the municipality of Chaudfontaine in the province of Liège, Belgium.
  • B. Tatihou
    Tatihou is a small French island off the coast of Normandy known for its historic Vauban fortifications, maritime museum, and rich coastal birdlife.
  • C. Donges
    Donges is a commune in western France’s Loire-Atlantique department, known for its major oil refinery and industrial port facilities along the Loire River.
  • D. Lantheuil
    Lantheuil is a small commune in the Calvados department of the Normandy region in northwestern France.
  • E. Wattrelos
    Wattrelos is a commune in northern France near the Belgian border, known historically for its textile industry and cross-border cultural ties.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e157277e7881908d49f4874766b3b5 completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffcf1893388190800f013fab415ae7 completed May 10, 2026, 12:19 a.m.
NEDg Description generation batch_69ffd049952081909221df73d3555557 completed May 10, 2026, 12:24 a.m.
NED2 Entity disambiguation (via description) batch_69ffd10ab484819089cd94ef07cb8de5 completed May 10, 2026, 12:27 a.m.
Created at: April 10, 2026, 4:54 a.m.