Triple

T15751446
Position Surface form Disambiguated ID Type / Status
Subject Tennevoll E381854 entity
Predicate hasSchool P113 FINISHED
Object Lavangen school
Lavangen school is a local educational institution serving primary and/or lower secondary students in the village of Tennevoll in Lavangen Municipality, Norway.
E1175959 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: Lavangen school | Statement: [Tennevoll, hasSchool, Lavangen school]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lavangen school
Context triple: [Tennevoll, hasSchool, Lavangen school]
  • A. Morellbakken School
    Morellbakken School is an educational institution located in the Nordre Aker borough of Oslo, Norway.
  • B. Tåsen School
    Tåsen School is a primary and lower secondary school located in the Nordre Aker borough of Oslo, Norway.
  • C. Vanløse School
    Vanløse School is a primary and lower secondary school located in the Vanløse district of Copenhagen, Denmark.
  • D. Kjelsås School
    Kjelsås School is a primary and lower secondary school located in the Kjelsås area of the Nordre Aker borough in Oslo, Norway.
  • E. Stabekk primary school
    Stabekk primary school is a local elementary school serving young children in the Stabekk area of Norway.
  • 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: Lavangen school
Triple: [Tennevoll, hasSchool, Lavangen school]
Generated description
Lavangen school is a local educational institution serving primary and/or lower secondary students in the village of Tennevoll in Lavangen Municipality, Norway.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lavangen school
Target entity description: Lavangen school is a local educational institution serving primary and/or lower secondary students in the village of Tennevoll in Lavangen Municipality, Norway.
  • A. Morellbakken School
    Morellbakken School is an educational institution located in the Nordre Aker borough of Oslo, Norway.
  • B. Tåsen School
    Tåsen School is a primary and lower secondary school located in the Nordre Aker borough of Oslo, Norway.
  • C. Vanløse School
    Vanløse School is a primary and lower secondary school located in the Vanløse district of Copenhagen, Denmark.
  • D. Kjelsås School
    Kjelsås School is a primary and lower secondary school located in the Kjelsås area of the Nordre Aker borough in Oslo, Norway.
  • E. Stabekk primary school
    Stabekk primary school is a local elementary school serving young children in the Stabekk area of Norway.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e05030e31081908c307a8dc7067db4 completed April 16, 2026, 2:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff876d48588190afec7722cca25633 completed May 9, 2026, 7:13 p.m.
NEDg Description generation batch_69ff8b6c44d081908e35ca17b5ce2189 completed May 9, 2026, 7:30 p.m.
NED2 Entity disambiguation (via description) batch_69ff8ca1c1f08190aeb6f7421d54c2de completed May 9, 2026, 7:36 p.m.
Created at: April 10, 2026, 4:47 a.m.