Triple

T5806811
Position Surface form Disambiguated ID Type / Status
Subject Sastamala E128764 entity
Predicate hasNeighbour P5707 FINISHED
Object Lavia
Lavia is a small municipality in southwestern Finland known for its rural landscapes and proximity to the town of Sastamala.
 E553710 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: Lavia | Statement: [Sastamala, hasNeighbour, Lavia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lavia
Context triple: [Sastamala, hasNeighbour, Lavia]
  • A. Laleia
    Laleia is a town in northern Timor-Leste known as the birthplace of independence leader and former president Xanana Gusmão.
  • B. Vayavi
    Vayavi is a lesser-known figure in Hindu mythology identified as the consort of the wind god Vayu.
  • C. Tairua
    Tairua is a small coastal town and popular holiday destination on New Zealand’s Coromandel Peninsula, known for its beaches, fishing, and scenic views of nearby offshore islands.
  • D. Vangunu
    Vangunu is an Oceanic language of the Meso-Melanesian group spoken on Vangunu Island in the Solomon Islands.
  • E. Lenaia
    Lenaia was an ancient Athenian winter festival in honor of Dionysus, featuring dramatic competitions and celebrations of wine and fertility.
  • 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: Lavia
Triple: [Sastamala, hasNeighbour, Lavia]
Generated description
Lavia is a small municipality in southwestern Finland known for its rural landscapes and proximity to the town of Sastamala.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lavia
Target entity description: Lavia is a small municipality in southwestern Finland known for its rural landscapes and proximity to the town of Sastamala.
  • A. Laleia
    Laleia is a town in northern Timor-Leste known as the birthplace of independence leader and former president Xanana Gusmão.
  • B. Vayavi
    Vayavi is a lesser-known figure in Hindu mythology identified as the consort of the wind god Vayu.
  • C. Tairua
    Tairua is a small coastal town and popular holiday destination on New Zealand’s Coromandel Peninsula, known for its beaches, fishing, and scenic views of nearby offshore islands.
  • D. Vangunu
    Vangunu is an Oceanic language of the Meso-Melanesian group spoken on Vangunu Island in the Solomon Islands.
  • E. Lenaia
    Lenaia was an ancient Athenian winter festival in honor of Dionysus, featuring dramatic competitions and celebrations of wine and fertility.
  • 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_69c00846a0d881909e46841f8e156b64 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02b15d8108190b434da42631c4e0c completed March 22, 2026, 5:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0b0dc78a481908fb97c88b2f642fc completed March 23, 2026, 3:17 a.m.
NEDg Description generation batch_69c0b1cb731481909de9c3fde3595b7b completed March 23, 2026, 3:21 a.m.
NED2 Entity disambiguation (via description) batch_69c0b27f53608190b2a1f78e3cd1b634 completed March 23, 2026, 3:24 a.m.
Created at: March 22, 2026, 3:52 p.m.