Triple

T11017361
Position Surface form Disambiguated ID Type / Status
Subject Hæren E260396 entity
Predicate garrison P75 FINISHED
Object Porsangmoen
Porsangmoen is a Norwegian Army military base and training area located in Porsanger, Finnmark, in northern Norway.
E900242 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: Porsangmoen | Statement: [Hæren, garrison, Porsangmoen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Porsangmoen
Context triple: [Hæren, garrison, Porsangmoen]
  • A. Jangsaengpo
    Jangsaengpo is a coastal district in Ulsan, South Korea, historically known as a major whaling port and now a center for marine and whale-related tourism.
  • B. Balaesang
    Balaesang is an Austronesian language of the Tomini–Tolitoli group spoken in Central Sulawesi, Indonesia.
  • C. Panggi
    Panggi is a subgroup or community within the larger Adi ethnic group of Arunachal Pradesh in northeastern India.
  • D. Ngaju
    Ngaju is an Austronesian language spoken primarily by the Ngaju Dayak people in Central Kalimantan on the island of Borneo in Indonesia.
  • E. Pagaruyung
    Pagaruyung is a historic royal city in West Sumatra that served as the seat of the Minangkabau kingdom and remains an important symbol of Minangkabau culture and heritage.
  • 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: Porsangmoen
Triple: [Hæren, garrison, Porsangmoen]
Generated description
Porsangmoen is a Norwegian Army military base and training area located in Porsanger, Finnmark, in northern Norway.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Porsangmoen
Target entity description: Porsangmoen is a Norwegian Army military base and training area located in Porsanger, Finnmark, in northern Norway.
  • A. Jangsaengpo
    Jangsaengpo is a coastal district in Ulsan, South Korea, historically known as a major whaling port and now a center for marine and whale-related tourism.
  • B. Balaesang
    Balaesang is an Austronesian language of the Tomini–Tolitoli group spoken in Central Sulawesi, Indonesia.
  • C. Panggi
    Panggi is a subgroup or community within the larger Adi ethnic group of Arunachal Pradesh in northeastern India.
  • D. Ngaju
    Ngaju is an Austronesian language spoken primarily by the Ngaju Dayak people in Central Kalimantan on the island of Borneo in Indonesia.
  • E. Pagaruyung
    Pagaruyung is a historic royal city in West Sumatra that served as the seat of the Minangkabau kingdom and remains an important symbol of Minangkabau culture and heritage.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797a7f4a881908232f99d18d95149 completed April 9, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69e374d371ec8190aba9e77346c6e876 completed April 18, 2026, 12:10 p.m.
NEDg Description generation batch_69e37ab6ca788190ac41f9494ad9a47f completed April 18, 2026, 12:36 p.m.
NED2 Entity disambiguation (via description) batch_69e37c9439fc8190a69cfb1a13da4c19 completed April 18, 2026, 12:44 p.m.
Created at: April 8, 2026, 9:25 p.m.