Triple

T20137760
Position Surface form Disambiguated ID Type / Status
Subject Lennart Meri E491068 entity
Predicate familyName P18 FINISHED
Object Meri
Meri is an Estonian surname most prominently associated with Lennart Meri, the former president of Estonia and noted writer and filmmaker.
 E1413443 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: Meri | Statement: [Lennart Meri, familyName, Meri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Meri
Context triple: [Lennart Meri, familyName, Meri]
  • A. Mera
    Mera is a powerful Atlantean warrior and sorceress from DC Comics, best known as Aquaman’s ally and queen of Atlantis.
  • B. Mera
    Mera is a town in Ecuador that serves as the administrative and commercial center of Mera Canton in Pastaza Province.
  • C. Mere
    Mere is a small historic market town in southwest Wiltshire, England, known for its rural setting near the borders of Dorset and Somerset.
  • D. Mere
    Mere is a village and civil parish in Cheshire, England, known for its affluent residential character and proximity to the town of Knutsford.
  • E. Meije
    Meije is a prominent peak in the French Alps renowned for its dramatic, glaciated faces and challenging mountaineering routes.
  • 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: Meri
Triple: [Lennart Meri, familyName, Meri]
Generated description
Meri is an Estonian surname most prominently associated with Lennart Meri, the former president of Estonia and noted writer and filmmaker.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Meri
Target entity description: Meri is an Estonian surname most prominently associated with Lennart Meri, the former president of Estonia and noted writer and filmmaker.
  • A. Mera
    Mera is a powerful Atlantean warrior and sorceress from DC Comics, best known as Aquaman’s ally and queen of Atlantis.
  • B. Mera
    Mera is a town in Ecuador that serves as the administrative and commercial center of Mera Canton in Pastaza Province.
  • C. Mere
    Mere is a small historic market town in southwest Wiltshire, England, known for its rural setting near the borders of Dorset and Somerset.
  • D. Mere
    Mere is a village and civil parish in Cheshire, England, known for its affluent residential character and proximity to the town of Knutsford.
  • E. Meije
    Meije is a prominent peak in the French Alps renowned for its dramatic, glaciated faces and challenging mountaineering routes.
  • 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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6676879f48190a59da04393d2a8cc completed April 20, 2026, 5:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a082de4bba88190a7d20a03826cbff0 completed May 16, 2026, 8:42 a.m.
NEDg Description generation batch_6a082ee3aafc819088a14b0a5d655072 completed May 16, 2026, 8:46 a.m.
NED2 Entity disambiguation (via description) batch_6a082f70e24881909c43a85289df4976 completed May 16, 2026, 8:48 a.m.
Created at: April 11, 2026, 11:32 p.m.