Triple

T5066296
Position Surface form Disambiguated ID Type / Status
Subject Harku Parish E114151 entity
Predicate containsSettlement P847 FINISHED
Object Harku
Harku is a small settlement in northern Estonia located within Harku Parish, near the capital city of Tallinn.
E489997 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: Harku | Statement: [Harku Parish, containsSettlement, Harku]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harku
Context triple: [Harku Parish, containsSettlement, Harku]
  • A. Hekari
    Hekari is a regional dialect of the Kurmanji variety of the Kurdish language, spoken in parts of the Hakkari region.
  • B. Hacha-Kekan
    Hacha-Kekan is a traditional cultural festival of the Karbi people that showcases their indigenous rituals, music, dance, and communal celebrations.
  • C. Sirokakara
    Sirokakara is a small settlement located on Choiseul Island in the Solomon Islands.
  • D. Kogarah
    Kogarah is a suburb in southern Sydney, New South Wales, Australia, known as a residential and commercial hub in the St George area.
  • E. Hayakaken
    Hayakaken is a rechargeable contactless smart card used for public transportation in the Fukuoka area of Japan.
  • 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: Harku
Triple: [Harku Parish, containsSettlement, Harku]
Generated description
Harku is a small settlement in northern Estonia located within Harku Parish, near the capital city of Tallinn.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Harku
Target entity description: Harku is a small settlement in northern Estonia located within Harku Parish, near the capital city of Tallinn.
  • A. Hekari
    Hekari is a regional dialect of the Kurmanji variety of the Kurdish language, spoken in parts of the Hakkari region.
  • B. Hacha-Kekan
    Hacha-Kekan is a traditional cultural festival of the Karbi people that showcases their indigenous rituals, music, dance, and communal celebrations.
  • C. Sirokakara
    Sirokakara is a small settlement located on Choiseul Island in the Solomon Islands.
  • D. Kogarah
    Kogarah is a suburb in southern Sydney, New South Wales, Australia, known as a residential and commercial hub in the St George area.
  • E. Hayakaken
    Hayakaken is a rechargeable contactless smart card used for public transportation in the Fukuoka area of Japan.
  • 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_69bd443c0c8c81908663b77afb28e165 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd749aceac8190817278266308fd64 completed March 20, 2026, 4:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea49d917081909ead17eed3f8af90 completed March 21, 2026, 2:01 p.m.
NEDg Description generation batch_69bea525d9088190b0b655687dd27630 completed March 21, 2026, 2:03 p.m.
NED2 Entity disambiguation (via description) batch_69bea594850881909cd683670b63a079 completed March 21, 2026, 2:05 p.m.
Created at: March 20, 2026, 1:38 p.m.