Triple

T21258803
Position Surface form Disambiguated ID Type / Status
Subject Central Mazanderani E523940 entity
Predicate hasAlternativeName P39 FINISHED
Object Central Mazani
Central Mazani is a dialect of the Mazanderani language spoken in the central regions of Iran’s Mazandaran province.
E1475305 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: Central Mazani | Statement: [Central Mazanderani, hasAlternativeName, Central Mazani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Central Mazani
Context triple: [Central Mazanderani, hasAlternativeName, Central Mazani]
  • A. Migama
    Migama is an Afro-Asiatic (Chadic) language spoken in parts of Chad.
  • B. Mazilu
    Mazilu is a Romanian surname borne by various notable figures in fields such as politics, law, and the arts.
  • C. Machang
    Machang is a town and administrative district in the Malaysian state of Kelantan, known for its semi-urban character and role as a local commercial and educational hub.
  • D. Kayamandi
    Kayamandi is a predominantly Black township on the outskirts of Stellenbosch in South Africa, known for its vibrant community life and history rooted in apartheid-era urban planning.
  • E. Mokama
    Mokama is a town in the Patna district of Bihar, India, situated along the Ganges River and known as an important regional transport and industrial hub.
  • 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: Central Mazani
Triple: [Central Mazanderani, hasAlternativeName, Central Mazani]
Generated description
Central Mazani is a dialect of the Mazanderani language spoken in the central regions of Iran’s Mazandaran province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Central Mazani
Target entity description: Central Mazani is a dialect of the Mazanderani language spoken in the central regions of Iran’s Mazandaran province.
  • A. Migama
    Migama is an Afro-Asiatic (Chadic) language spoken in parts of Chad.
  • B. Mazilu
    Mazilu is a Romanian surname borne by various notable figures in fields such as politics, law, and the arts.
  • C. Machang
    Machang is a town and administrative district in the Malaysian state of Kelantan, known for its semi-urban character and role as a local commercial and educational hub.
  • D. Kayamandi
    Kayamandi is a predominantly Black township on the outskirts of Stellenbosch in South Africa, known for its vibrant community life and history rooted in apartheid-era urban planning.
  • E. Mokama
    Mokama is a town in the Patna district of Bihar, India, situated along the Ganges River and known as an important regional transport and industrial hub.
  • 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_69e0b5156d7881909bd4f83676590715 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e735e477d08190be17ad5384d69a80 completed April 21, 2026, 8:31 a.m.
NED1 Entity disambiguation (via context triple) batch_6a098ffc53b08190b3d6ed00c7d104d6 completed May 17, 2026, 9:53 a.m.
NEDg Description generation batch_6a0991b637288190912b5557826b2a9b completed May 17, 2026, 10 a.m.
NED2 Entity disambiguation (via description) batch_6a0992aa17408190bef9b0f1477d3e1f completed May 17, 2026, 10:04 a.m.
Created at: April 16, 2026, 3:59 p.m.