Triple

T15477075
Position Surface form Disambiguated ID Type / Status
Subject Gilan Province E376809 entity
Predicate hasMajorCity P316 FINISHED
Object Fuman
Fuman is a city in northern Iran known for its lush rice fields, traditional cookies, and proximity to the scenic Masuleh village in Gilan Province.
 E1159632 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: Fuman | Statement: [Gilan Province, hasMajorCity, Fuman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Fuman
Context triple: [Gilan Province, hasMajorCity, Fuman]
  • A. Yuman
    Yuman is a Native American language family of the southwestern United States and northwestern Mexico, encompassing several related indigenous languages and peoples.
  • B. Vangunu
    Vangunu is an Oceanic language of the Meso-Melanesian group spoken on Vangunu Island in the Solomon Islands.
  • C. Luman
    Luman is a masculine given name of English origin, historically borne by figures such as the 19th-century American art patron Luman Reed.
  • D. Fondani
    Fondani are the inhabitants or natives of the Italian town of Fondi, located in the Lazio region.
  • E. Yámana
    The Yámana are an Indigenous people of the southernmost regions of South America, traditionally known as seafaring hunter-gatherers of the Tierra del Fuego archipelago.
  • 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: Fuman
Triple: [Gilan Province, hasMajorCity, Fuman]
Generated description
Fuman is a city in northern Iran known for its lush rice fields, traditional cookies, and proximity to the scenic Masuleh village in Gilan Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Fuman
Target entity description: Fuman is a city in northern Iran known for its lush rice fields, traditional cookies, and proximity to the scenic Masuleh village in Gilan Province.
  • A. Yuman
    Yuman is a Native American language family of the southwestern United States and northwestern Mexico, encompassing several related indigenous languages and peoples.
  • B. Vangunu
    Vangunu is an Oceanic language of the Meso-Melanesian group spoken on Vangunu Island in the Solomon Islands.
  • C. Luman
    Luman is a masculine given name of English origin, historically borne by figures such as the 19th-century American art patron Luman Reed.
  • D. Fondani
    Fondani are the inhabitants or natives of the Italian town of Fondi, located in the Lazio region.
  • E. Yámana
    The Yámana are an Indigenous people of the southernmost regions of South America, traditionally known as seafaring hunter-gatherers of the Tierra del Fuego archipelago.
  • 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_69d85cd21dcc81908646251b1c26ea00 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f88a5dc8190a2d7830748e29180 completed April 16, 2026, 1:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff2d0b3e7881908f195701fe222371 completed May 9, 2026, 12:48 p.m.
NEDg Description generation batch_69ff2e4010dc8190b0f81d03acf8ba41 completed May 9, 2026, 12:53 p.m.
NED2 Entity disambiguation (via description) batch_69ff310c2d5c819093295c45307176ec completed May 9, 2026, 1:05 p.m.
Created at: April 10, 2026, 3:34 a.m.