Triple

T12543126
Position Surface form Disambiguated ID Type / Status
Subject Shirak Province E299892 entity
Predicate containsTown P847 FINISHED
Object Maralik
Maralik is a small town in northwestern Armenia known for its agricultural surroundings and location within the Shirak region.
 E989178 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: Maralik | Statement: [Shirak Province, containsTown, Maralik]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Maralik
Context triple: [Shirak Province, containsTown, Maralik]
  • A. Maleka
    Maleka is a feminine given name, typically considered a variant spelling of Malika and used in various cultures.
  • B. Mi'ilya
    Mi'ilya is a village in northern Israel, notable for its predominantly Christian Arab population and its location near the city of Ma'alot-Tarshiha.
  • C. Mella
    Mella is a Spanish-language surname most notably associated with Cuban revolutionary leader Julio Antonio Mella.
  • D. Marale
    Marale is a small municipality located in the Francisco Morazán Department of central Honduras.
  • E. Dorla
    Dorla are an indigenous Adivasi community of the Bastar region in central India, known for their distinct cultural traditions, language, and close relationship with forest-based livelihoods.
  • 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: Maralik
Triple: [Shirak Province, containsTown, Maralik]
Generated description
Maralik is a small town in northwestern Armenia known for its agricultural surroundings and location within the Shirak region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Maralik
Target entity description: Maralik is a small town in northwestern Armenia known for its agricultural surroundings and location within the Shirak region.
  • A. Maleka
    Maleka is a feminine given name, typically considered a variant spelling of Malika and used in various cultures.
  • B. Mi'ilya
    Mi'ilya is a village in northern Israel, notable for its predominantly Christian Arab population and its location near the city of Ma'alot-Tarshiha.
  • C. Mella
    Mella is a Spanish-language surname most notably associated with Cuban revolutionary leader Julio Antonio Mella.
  • D. Marale
    Marale is a small municipality located in the Francisco Morazán Department of central Honduras.
  • E. Dorla
    Dorla are an indigenous Adivasi community of the Bastar region in central India, known for their distinct cultural traditions, language, and close relationship with forest-based livelihoods.
  • 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_69d6ada707008190aaec1238117c9379 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9547d6df4819080db8415d386ed38 completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6557e6d4c81909ed54a039e92a160 completed May 2, 2026, 7:50 p.m.
NEDg Description generation batch_69f6566f40c08190baec227fb660c948 completed May 2, 2026, 7:54 p.m.
NED2 Entity disambiguation (via description) batch_69f657aa1bf48190a884e0dfce31e30e completed May 2, 2026, 7:59 p.m.
Created at: April 8, 2026, 9:57 p.m.