Triple

T1845911
Position Surface form Disambiguated ID Type / Status
Subject Danish Army E41281 entity
Predicate garrison P75 FINISHED
Object Skive
Skive is a town in northwestern Jutland, Denmark, known for its military presence as well as its role as a regional commercial and cultural center.
 E205948 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: Skive | Statement: [Danish Army, garrison, Skive]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Skive
Context triple: [Danish Army, garrison, Skive]
  • A. Odeo
    Odeo was an early podcasting startup co-founded by the team behind Obvious Corporation that played a key role in the creation of Twitter.
  • B. Rockanje
    Rockanje is a coastal village in the western Netherlands known for its North Sea beaches and dunes, located on the island of Voorne-Putten in the province of South Holland.
  • C. Kill the DJ
    "Kill the DJ" is a punk rock song by Green Day from their 2012 album ¡Uno!, noted for its dance-punk style and politically tinged lyrics.
  • D. Dranse
    The Dranse is a river in the Haute-Savoie region of France that flows from the Alps into Lake Geneva near Thonon-les-Bains.
  • E. Rockpile
    Rockpile is a renowned American Viticultural Area in Sonoma County, California, known for its high-elevation vineyards and intensely flavored Zinfandel wines.
  • 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: Skive
Triple: [Danish Army, garrison, Skive]
Generated description
Skive is a town in northwestern Jutland, Denmark, known for its military presence as well as its role as a regional commercial and cultural center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Skive
Target entity description: Skive is a town in northwestern Jutland, Denmark, known for its military presence as well as its role as a regional commercial and cultural center.
  • A. Odeo
    Odeo was an early podcasting startup co-founded by the team behind Obvious Corporation that played a key role in the creation of Twitter.
  • B. Rockanje
    Rockanje is a coastal village in the western Netherlands known for its North Sea beaches and dunes, located on the island of Voorne-Putten in the province of South Holland.
  • C. Kill the DJ
    "Kill the DJ" is a punk rock song by Green Day from their 2012 album ¡Uno!, noted for its dance-punk style and politically tinged lyrics.
  • D. Dranse
    The Dranse is a river in the Haute-Savoie region of France that flows from the Alps into Lake Geneva near Thonon-les-Bains.
  • E. Rockpile
    Rockpile is a renowned American Viticultural Area in Sonoma County, California, known for its high-elevation vineyards and intensely flavored Zinfandel wines.
  • 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_69a88648cd44819093303206d96d76ad completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb051640c819088a8b28a03f57331 completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69adc9c070548190af52d3feaa3aead2 completed March 8, 2026, 7:10 p.m.
NEDg Description generation batch_69adcb1466788190bdcb50107d838f83 completed March 8, 2026, 7:16 p.m.
NED2 Entity disambiguation (via description) batch_69adcbf5b0b881909d43c748034481f4 completed March 8, 2026, 7:20 p.m.
Created at: March 4, 2026, 7:33 p.m.