Triple

T750667
Position Surface form Disambiguated ID Type / Status
Subject Friesland E15439 entity
Predicate hasPart P35 FINISHED
Object Dokkum
Dokkum is a historic fortified town in the northern Netherlands, known as one of the Frisian Eleven Cities and for its association with the martyrdom of Saint Boniface.
 E89981 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: Dokkum | Statement: [Friesland, hasPart, Dokkum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dokkum
Context triple: [Friesland, hasPart, Dokkum]
  • A. Faro
    Faro is a historic coastal city in southern Portugal that serves as the capital of the Algarve region and a major gateway for tourism.
  • B. Køpmannæhafn
    Køpmannæhafn is the historical Danish name for the city now known as Copenhagen, reflecting its origins as a merchant harbor.
  • C. Arendal
    Arendal is a coastal town and municipality in southern Norway known historically as a regional political and trading center.
  • D. Haugesund
    Haugesund is a coastal city in southwestern Norway known for its maritime heritage, shipbuilding industry, and annual film and jazz festivals.
  • E. Hvalsey
    Hvalsey is the best-preserved Norse ruin site in Greenland, known for its stone church and remnants of a medieval farming settlement.
  • 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: Dokkum
Triple: [Friesland, hasPart, Dokkum]
Generated description
Dokkum is a historic fortified town in the northern Netherlands, known as one of the Frisian Eleven Cities and for its association with the martyrdom of Saint Boniface.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dokkum
Target entity description: Dokkum is a historic fortified town in the northern Netherlands, known as one of the Frisian Eleven Cities and for its association with the martyrdom of Saint Boniface.
  • A. Faro
    Faro is a historic coastal city in southern Portugal that serves as the capital of the Algarve region and a major gateway for tourism.
  • B. Køpmannæhafn
    Køpmannæhafn is the historical Danish name for the city now known as Copenhagen, reflecting its origins as a merchant harbor.
  • C. Arendal
    Arendal is a coastal town and municipality in southern Norway known historically as a regional political and trading center.
  • D. Haugesund
    Haugesund is a coastal city in southwestern Norway known for its maritime heritage, shipbuilding industry, and annual film and jazz festivals.
  • E. Hvalsey
    Hvalsey is the best-preserved Norse ruin site in Greenland, known for its stone church and remnants of a medieval farming settlement.
  • 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_69a493599a0081908da65f3407af1ef2 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a64adf2c81908e48090be35dd9d9 completed March 1, 2026, 8:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69a65e4086e481908d0ea29729d92d67 completed March 3, 2026, 4:06 a.m.
NEDg Description generation batch_69a65eeaa34481909b0deac860fbadfc completed March 3, 2026, 4:09 a.m.
NED2 Entity disambiguation (via description) batch_69a65f7b09b08190bf38f02a912b2276 completed March 3, 2026, 4:11 a.m.
Created at: March 1, 2026, 7:37 p.m.