Triple

T11405224
Position Surface form Disambiguated ID Type / Status
Subject Elmira E270219 entity
Predicate hasDiminutive P456 FINISHED
Object Elmi
Elmi is a diminutive form of the given name Elmira, often used as an affectionate nickname.
 E923910 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: Elmi | Statement: [Elmira, hasDiminutive, Elmi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Elmi
Context triple: [Elmira, hasDiminutive, Elmi]
  • A. Ellmau
    Ellmau is a popular Austrian alpine village and ski resort known for its scenic setting in the Kitzbühel Alps and extensive winter sports and hiking opportunities.
  • B. Ilami
    Ilami is a regional variety of Southern Kurdish spoken primarily in and around the city of Ilam in western Iran.
  • C. Eimi
    Eimi is an experimental, stream-of-consciousness travelogue by E. E. Cummings that chronicles his journey through Soviet Russia in 1931.
  • D. Lemi
    Lemi is a small rural municipality in southeastern Finland known for its lakes, forests, and traditional Karelian culture.
  • E. Gelimar
    Gelimar was the last king of the Vandal Kingdom in North Africa, known for his defeat by the Byzantine general Belisarius in the 6th century.
  • 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: Elmi
Triple: [Elmira, hasDiminutive, Elmi]
Generated description
Elmi is a diminutive form of the given name Elmira, often used as an affectionate nickname.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Elmi
Target entity description: Elmi is a diminutive form of the given name Elmira, often used as an affectionate nickname.
  • A. Ellmau
    Ellmau is a popular Austrian alpine village and ski resort known for its scenic setting in the Kitzbühel Alps and extensive winter sports and hiking opportunities.
  • B. Ilami
    Ilami is a regional variety of Southern Kurdish spoken primarily in and around the city of Ilam in western Iran.
  • C. Eimi
    Eimi is an experimental, stream-of-consciousness travelogue by E. E. Cummings that chronicles his journey through Soviet Russia in 1931.
  • D. Lemi
    Lemi is a small rural municipality in southeastern Finland known for its lakes, forests, and traditional Karelian culture.
  • E. Gelimar
    Gelimar was the last king of the Vandal Kingdom in North Africa, known for his defeat by the Byzantine general Belisarius in the 6th century.
  • 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_69d6aaddeaa8819088b30ef7b50598c9 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8014c820c81908538ba4a08e13230 completed April 9, 2026, 7:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69e58d56608481908dbb19daa2abfc0a completed April 20, 2026, 2:20 a.m.
NEDg Description generation batch_69e59777b1208190a33a50da286535ee completed April 20, 2026, 3:03 a.m.
NED2 Entity disambiguation (via description) batch_69e5a3cf9d388190944340af484b3a54 completed April 20, 2026, 3:55 a.m.
Created at: April 8, 2026, 9:34 p.m.