Triple

T1829946
Position Surface form Disambiguated ID Type / Status
Subject Southwest Finland E40737 entity
Predicate ISOCode P208 FINISHED
Object FI-02
FI-02 is the ISO 3166-2 code that designates the region of Southwest Finland within the national subdivision system of Finland.
 E203451 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: FI-02 | Statement: [Southwest Finland, ISOCode, FI-02]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FI-02
Context triple: [Southwest Finland, ISOCode, FI-02]
  • A. FIO
    FIO is the acronym for the Federal Insurance Office, a U.S. Treasury Department agency that monitors the insurance industry and advises on national and international insurance policy.
  • B. FiO
    FiO is the commonly used abbreviation for Frontiers in Optics, a major annual conference focused on advances in optical science and engineering.
  • C. FIAS
    FIAS is the international governing body responsible for overseeing and promoting the combat sport of sambo worldwide.
  • D. F82
    F82 is the pennant number assigned to HMS Sikh, a British Royal Navy Tribal-class destroyer that served during the Second World War.
  • E. GAFI
    GAFI is the French acronym for the Financial Action Task Force, an intergovernmental body that sets global standards to combat money laundering, terrorist financing, and related financial crimes.
  • 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: FI-02
Triple: [Southwest Finland, ISOCode, FI-02]
Generated description
FI-02 is the ISO 3166-2 code that designates the region of Southwest Finland within the national subdivision system of Finland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FI-02
Target entity description: FI-02 is the ISO 3166-2 code that designates the region of Southwest Finland within the national subdivision system of Finland.
  • A. FIO
    FIO is the acronym for the Federal Insurance Office, a U.S. Treasury Department agency that monitors the insurance industry and advises on national and international insurance policy.
  • B. FiO
    FiO is the commonly used abbreviation for Frontiers in Optics, a major annual conference focused on advances in optical science and engineering.
  • C. FIAS
    FIAS is the international governing body responsible for overseeing and promoting the combat sport of sambo worldwide.
  • D. F82
    F82 is the pennant number assigned to HMS Sikh, a British Royal Navy Tribal-class destroyer that served during the Second World War.
  • E. GAFI
    GAFI is the French acronym for the Financial Action Task Force, an intergovernmental body that sets global standards to combat money laundering, terrorist financing, and related financial crimes.
  • 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_69a8864644bc8190b2358ab897194ac1 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb0144cc08190abd1a6cf44e64daf completed March 7, 2026, 4:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69adbf6d49988190b8cb1773609a379b completed March 8, 2026, 6:26 p.m.
NEDg Description generation batch_69adc07fff60819092b10dd0e417ac5a completed March 8, 2026, 6:31 p.m.
NED2 Entity disambiguation (via description) batch_69adc0fd79c48190864f53a90517edc6 completed March 8, 2026, 6:33 p.m.
Created at: March 4, 2026, 7:32 p.m.