Triple

T632865
Position Surface form Disambiguated ID Type / Status
Subject Greenlandic Norse E15958 entity
Predicate religiousCenter P1191 FINISHED
Object Gardar
Gardar was the principal ecclesiastical and administrative center of the Norse settlements in medieval Greenland, serving as the seat of the bishopric.
 E81700 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: Gardar | Statement: [Greenlandic Norse, religiousCenter, Gardar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gardar
Context triple: [Greenlandic Norse, religiousCenter, Gardar]
  • A. Pàl
    Pàl is a variant form of the given name Paul, used in certain languages or regional contexts.
  • B. Övdalian
    Övdalian is a North Germanic language variety spoken in the Älvdalen region of Sweden, noted for preserving many archaic features lost in standard Swedish.
  • C. Troms
    Troms was a former county in northern Norway known for its Arctic landscapes, coastal fjords, and the city of Tromsø.
  • D. Jóhan
    Jóhan is a given name, primarily used in Faroese and other Nordic contexts, that corresponds to the name Johan.
  • E. Stetind
    Stetind is a distinctive, obelisk-shaped granite mountain in Nordland, Norway, often called Norway’s national mountain and renowned among climbers and photographers.
  • 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: Gardar
Triple: [Greenlandic Norse, religiousCenter, Gardar]
Generated description
Gardar was the principal ecclesiastical and administrative center of the Norse settlements in medieval Greenland, serving as the seat of the bishopric.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gardar
Target entity description: Gardar was the principal ecclesiastical and administrative center of the Norse settlements in medieval Greenland, serving as the seat of the bishopric.
  • A. Pàl
    Pàl is a variant form of the given name Paul, used in certain languages or regional contexts.
  • B. Övdalian
    Övdalian is a North Germanic language variety spoken in the Älvdalen region of Sweden, noted for preserving many archaic features lost in standard Swedish.
  • C. Troms
    Troms was a former county in northern Norway known for its Arctic landscapes, coastal fjords, and the city of Tromsø.
  • D. Jóhan
    Jóhan is a given name, primarily used in Faroese and other Nordic contexts, that corresponds to the name Johan.
  • E. Stetind
    Stetind is a distinctive, obelisk-shaped granite mountain in Nordland, Norway, often called Norway’s national mountain and renowned among climbers and photographers.
  • 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_69a4935c131c8190a5378c6bf101e8cc completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49ec3b6488190aa0dce216c089a2e completed March 1, 2026, 8:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69a58a6eeb688190b950e3c4fb5962f8 completed March 2, 2026, 1:02 p.m.
NEDg Description generation batch_69a58bca7d688190b6f9486838228f29 completed March 2, 2026, 1:08 p.m.
NED2 Entity disambiguation (via description) batch_69a5907b71c481908c59141ba7703a74 completed March 2, 2026, 1:28 p.m.
Created at: March 1, 2026, 7:35 p.m.