Triple

T5989312
Position Surface form Disambiguated ID Type / Status
Subject Saare County E133304 entity
Predicate contains P35 FINISHED
Object Abruka
Abruka is a small Estonian island in the Baltic Sea known for its dense broadleaf forest and tranquil, sparsely populated landscape.
 E561675 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: Abruka | Statement: [Saare County, contains, Abruka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Abruka
Context triple: [Saare County, contains, Abruka]
  • A. Auron
    Auron is a river in central France that flows through the Cher department and joins the Yèvre near the city of Bourges.
  • B. Auron
    Auron is a French ski resort village in the southern Alps known for its extensive slopes and proximity to Nice.
  • C. Raskhan
    Raskhan was a 16th–17th century Indian poet and devotee of Krishna, renowned for his lyrical Braj Bhasha compositions celebrating bhakti (devotional love).
  • D. Abiel
    Abiel is a biblical figure mentioned in the Old Testament as an ancestor in the lineage of King Saul.
  • E. Azarethes
    Azarethes was a prominent Sasanian Persian general noted for his role in the Iberian War against the Eastern Roman (Byzantine) Empire.
  • 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: Abruka
Triple: [Saare County, contains, Abruka]
Generated description
Abruka is a small Estonian island in the Baltic Sea known for its dense broadleaf forest and tranquil, sparsely populated landscape.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Abruka
Target entity description: Abruka is a small Estonian island in the Baltic Sea known for its dense broadleaf forest and tranquil, sparsely populated landscape.
  • A. Auron
    Auron is a river in central France that flows through the Cher department and joins the Yèvre near the city of Bourges.
  • B. Auron
    Auron is a French ski resort village in the southern Alps known for its extensive slopes and proximity to Nice.
  • C. Raskhan
    Raskhan was a 16th–17th century Indian poet and devotee of Krishna, renowned for his lyrical Braj Bhasha compositions celebrating bhakti (devotional love).
  • D. Abiel
    Abiel is a biblical figure mentioned in the Old Testament as an ancestor in the lineage of King Saul.
  • E. Azarethes
    Azarethes was a prominent Sasanian Persian general noted for his role in the Iberian War against the Eastern Roman (Byzantine) Empire.
  • 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_69c0087010d081908bb8142342d63330 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04dc76fd481908cc3f327e532a1a6 completed March 22, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1085ac1bc8190a828d3841098cc23 completed March 23, 2026, 9:31 a.m.
NEDg Description generation batch_69c10aab4d0c8190ae467f8c7c945196 completed March 23, 2026, 9:40 a.m.
NED2 Entity disambiguation (via description) batch_69c10b19705c8190a1d9ee17b1c5833f completed March 23, 2026, 9:42 a.m.
Created at: March 22, 2026, 4:04 p.m.