Triple

T21545471
Position Surface form Disambiguated ID Type / Status
Subject Sognsvann station E531611 entity
Predicate hasStationCode P1289 FINISHED
Object SVN
SVN is the station code for Sognsvann station on the Oslo Metro system in Norway.
 E1490679 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: SVN | Statement: [Sognsvann station, hasStationCode, SVN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SVN
Context triple: [Sognsvann station, hasStationCode, SVN]
  • A. SVN
    SVN is the IATA airport code for Hunter Army Airfield, a U.S. military airfield located near Savannah, Georgia.
  • B. SVN
    SVN is the three-letter ISO 3166-1 alpha-3 country code assigned to Slovenia.
  • C. Subversion
    Subversion is a centralized version control system used to manage and track changes to source code and other files in software development projects.
  • D. Concurrent Versions System
    Concurrent Versions System (CVS) is an early, widely used open-source version control system that manages changes to source code in collaborative software development.
  • E. COSVN
    COSVN was the clandestine headquarters and command center of the Viet Cong and North Vietnamese forces directing communist military and political operations in South Vietnam during the Vietnam War.
  • 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: SVN
Triple: [Sognsvann station, hasStationCode, SVN]
Generated description
SVN is the station code for Sognsvann station on the Oslo Metro system in Norway.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SVN
Target entity description: SVN is the station code for Sognsvann station on the Oslo Metro system in Norway.
  • A. SVN
    SVN is the IATA airport code for Hunter Army Airfield, a U.S. military airfield located near Savannah, Georgia.
  • B. SVN
    SVN is the three-letter ISO 3166-1 alpha-3 country code assigned to Slovenia.
  • C. Subversion
    Subversion is a centralized version control system used to manage and track changes to source code and other files in software development projects.
  • D. Concurrent Versions System
    Concurrent Versions System (CVS) is an early, widely used open-source version control system that manages changes to source code in collaborative software development.
  • E. COSVN
    COSVN was the clandestine headquarters and command center of the Viet Cong and North Vietnamese forces directing communist military and political operations in South Vietnam during the Vietnam War.
  • 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_69e0c45f17148190949c330ab9c27706 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeb58e38808190888f3501cf4fff7c completed April 27, 2026, 1:02 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09eedd845c819082acae7e6cd29f56 completed May 17, 2026, 4:37 p.m.
NEDg Description generation batch_6a09ef7271e081908a1cd70297376ae3 completed May 17, 2026, 4:40 p.m.
NED2 Entity disambiguation (via description) batch_6a09f00ec300819082ee644a512a9cdf completed May 17, 2026, 4:42 p.m.
Created at: April 16, 2026, 6:28 p.m.