Triple

T22827847
Position Surface form Disambiguated ID Type / Status
Subject Herlev E565708 entity
Predicate hasLandmark P105 FINISHED
Object Herlev Church
Herlev Church is a historic parish church in Herlev, Denmark, known for serving as a central religious and cultural landmark in the town.
E1558404 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: Herlev Church | Statement: [Herlev, hasLandmark, Herlev Church]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Herlev Church
Context triple: [Herlev, hasLandmark, Herlev Church]
  • A. Glostrup Church
    Glostrup Church is a historic parish church in the town of Glostrup, Denmark, serving as a central place of worship and local landmark.
  • B. Aabenraa Church
    Aabenraa Church is a historic Christian church located in the town of Aabenraa in southern Denmark.
  • C. Antvorskov Church
    Antvorskov Church is a historic parish church in Slagelse, Denmark, known for serving the local community and reflecting traditional Danish ecclesiastical architecture.
  • D. Borge Church
    Borge Church is a parish church in Norway serving the local Borge community as a center for Lutheran worship and congregational life.
  • E. Uranienborg Church
    Uranienborg Church is a historic Lutheran church in the Uranienborg neighborhood of Oslo, Norway, known for its distinctive architecture and prominent hilltop location.
  • 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: Herlev Church
Triple: [Herlev, hasLandmark, Herlev Church]
Generated description
Herlev Church is a historic parish church in Herlev, Denmark, known for serving as a central religious and cultural landmark in the town.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Herlev Church
Target entity description: Herlev Church is a historic parish church in Herlev, Denmark, known for serving as a central religious and cultural landmark in the town.
  • A. Glostrup Church
    Glostrup Church is a historic parish church in the town of Glostrup, Denmark, serving as a central place of worship and local landmark.
  • B. Aabenraa Church
    Aabenraa Church is a historic Christian church located in the town of Aabenraa in southern Denmark.
  • C. Antvorskov Church
    Antvorskov Church is a historic parish church in Slagelse, Denmark, known for serving the local community and reflecting traditional Danish ecclesiastical architecture.
  • D. Borge Church
    Borge Church is a parish church in Norway serving the local Borge community as a center for Lutheran worship and congregational life.
  • E. Uranienborg Church
    Uranienborg Church is a historic Lutheran church in the Uranienborg neighborhood of Oslo, Norway, known for its distinctive architecture and prominent hilltop location.
  • 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_69e24585ab1c81909b2b5065d15805d5 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e2914188190be6cdbd8167cd806 completed April 29, 2026, 3:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bae80bee881908b4945850529c624 completed May 19, 2026, 12:27 a.m.
NEDg Description generation batch_6a0bafa985508190b3206760d58c5018 completed May 19, 2026, 12:32 a.m.
NED2 Entity disambiguation (via description) batch_6a0bb052e8e881909cc9495be15cfb9f completed May 19, 2026, 12:35 a.m.
Created at: April 17, 2026, 3:34 p.m.