Triple

T3272428
Position Surface form Disambiguated ID Type / Status
Subject Mandane of Media E68679 entity
Predicate language P15 FINISHED
Object Median
Median is an ancient Northwestern Iranian language once spoken in the region of Media, in what is now northwestern Iran.
E342725 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: Median | Statement: [Mandane of Media, language, Median]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Median
Context triple: [Mandane of Media, language, Median]
  • A. Mediana
    Mediana is a late Roman imperial villa and archaeological complex near Niš, Serbia, notable as the birthplace estate of Emperor Constantine the Great.
  • B. Median forces
    The Median forces were the ancient military troops of the Median Empire that played a key role in toppling the Neo-Assyrian Empire, including the sack of Nineveh in 612 BCE.
  • C. Mitte
    Mitte is the central district of Berlin, Germany, known as the historic core of the city and home to many major landmarks and government institutions.
  • D. Center
    Center is the common shorthand term used in aviation to refer to an Air Route Traffic Control Center, which manages en route air traffic over large regions.
  • E. Middelaar
    Middelaar is a village in the Dutch province of Limburg, situated near the river Maas and close to the border with Germany.
  • 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: Median
Triple: [Mandane of Media, language, Median]
Generated description
Median is an ancient Northwestern Iranian language once spoken in the region of Media, in what is now northwestern Iran.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Median
Target entity description: Median is an ancient Northwestern Iranian language once spoken in the region of Media, in what is now northwestern Iran.
  • A. Mediana
    Mediana is a late Roman imperial villa and archaeological complex near Niš, Serbia, notable as the birthplace estate of Emperor Constantine the Great.
  • B. Median forces
    The Median forces were the ancient military troops of the Median Empire that played a key role in toppling the Neo-Assyrian Empire, including the sack of Nineveh in 612 BCE.
  • C. Mitte
    Mitte is the central district of Berlin, Germany, known as the historic core of the city and home to many major landmarks and government institutions.
  • D. Center
    Center is the common shorthand term used in aviation to refer to an Air Route Traffic Control Center, which manages en route air traffic over large regions.
  • E. Middelaar
    Middelaar is a village in the Dutch province of Limburg, situated near the river Maas and close to the border with Germany.
  • 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_69ad859b54f881909bf530d549caf2fd completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adaff6308881908886a44804a0bb09 completed March 8, 2026, 5:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28f0793e08190af55ee16e5091451 completed March 12, 2026, 10:01 a.m.
NEDg Description generation batch_69b296709f84819094fe9db721a44f83 completed March 12, 2026, 10:33 a.m.
NED2 Entity disambiguation (via description) batch_69b2d6c47e908190b5be5b33da358ade completed March 12, 2026, 3:07 p.m.
Created at: March 8, 2026, 3:10 p.m.