Triple

T17948642
Position Surface form Disambiguated ID Type / Status
Subject Eemsdelta E448769 entity
Predicate containsSettlement P847 FINISHED
Object Farmsum
Farmsum is a village in the province of Groningen in the Netherlands, now part of the municipality of Eemsdelta.
E1297576 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: Farmsum | Statement: [Eemsdelta, containsSettlement, Farmsum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Farmsum
Context triple: [Eemsdelta, containsSettlement, Farmsum]
  • A. Doldersum
    Doldersum is a small village in the Dutch province of Drenthe, known for its rural landscape and proximity to nature reserves.
  • B. Borssum
    Borssum is a district of the seaport city of Emden in Lower Saxony, Germany, known primarily as a residential area with local amenities.
  • C. La Haye farm
    La Haye farm is a fortified farmhouse on the Waterloo battlefield in Belgium that played a notable role in the 1815 battle between Napoleon and the Allied forces.
  • D. Bouckaert Farm
    Bouckaert Farm is a large equestrian and event venue in rural Georgia, known for hosting horse competitions and outdoor festivals.
  • E. Loppersum
    Loppersum is a village and former municipality in the province of Groningen in the Netherlands, known for its historic churches and its location in an area affected by gas-extraction-induced earthquakes.
  • 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: Farmsum
Triple: [Eemsdelta, containsSettlement, Farmsum]
Generated description
Farmsum is a village in the province of Groningen in the Netherlands, now part of the municipality of Eemsdelta.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Farmsum
Target entity description: Farmsum is a village in the province of Groningen in the Netherlands, now part of the municipality of Eemsdelta.
  • A. Doldersum
    Doldersum is a small village in the Dutch province of Drenthe, known for its rural landscape and proximity to nature reserves.
  • B. Borssum
    Borssum is a district of the seaport city of Emden in Lower Saxony, Germany, known primarily as a residential area with local amenities.
  • C. La Haye farm
    La Haye farm is a fortified farmhouse on the Waterloo battlefield in Belgium that played a notable role in the 1815 battle between Napoleon and the Allied forces.
  • D. Bouckaert Farm
    Bouckaert Farm is a large equestrian and event venue in rural Georgia, known for hosting horse competitions and outdoor festivals.
  • E. Loppersum
    Loppersum is a village and former municipality in the province of Groningen in the Netherlands, known for its historic churches and its location in an area affected by gas-extraction-induced earthquakes.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4afaac780819097434b20b1f155d2 completed April 19, 2026, 10:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03291c5e008190981dfef6aad81054 completed May 12, 2026, 1:20 p.m.
NEDg Description generation batch_6a032ae7f4808190ade6b20198aadcba completed May 12, 2026, 1:28 p.m.
NED2 Entity disambiguation (via description) batch_6a032b6033b48190b889bd4d98a58ea2 completed May 12, 2026, 1:30 p.m.
Created at: April 10, 2026, 10:21 a.m.