Triple

T8365996
Position Surface form Disambiguated ID Type / Status
Subject Vaspurakan E197126 entity
Predicate borders P224 FINISHED
Object Taron
Taron was a historical Armenian province and cultural region in the upper Euphrates area, known as an early center of Armenian Christianity and noble dynasties.
 E728074 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: Taron | Statement: [Vaspurakan, borders, Taron]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Taron
Context triple: [Vaspurakan, borders, Taron]
  • A. Taron
    Taron is a masculine given name most prominently associated with Welsh actor Taron Egerton.
  • B. Taron
    Taron is a high-speed multi-launch steel roller coaster located at Phantasialand in Germany, renowned for its intense layout and immersive themed environment.
  • C. Torell
    Torell is a given name and surname of Scandinavian origin, often considered a variant or diminutive of the name Tore.
  • D. Teron
    Teron is one of the traditional clans of the Karbi people, an indigenous ethnic group primarily inhabiting the Karbi Anglong region of Assam in Northeast India.
  • E. Tarak
    Tarak is the popular nickname of N. T. Rama Rao Jr., a leading Telugu film actor known for his roles in action and drama movies.
  • 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: Taron
Triple: [Vaspurakan, borders, Taron]
Generated description
Taron was a historical Armenian province and cultural region in the upper Euphrates area, known as an early center of Armenian Christianity and noble dynasties.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Taron
Target entity description: Taron was a historical Armenian province and cultural region in the upper Euphrates area, known as an early center of Armenian Christianity and noble dynasties.
  • A. Taron
    Taron is a masculine given name most prominently associated with Welsh actor Taron Egerton.
  • B. Taron
    Taron is a high-speed multi-launch steel roller coaster located at Phantasialand in Germany, renowned for its intense layout and immersive themed environment.
  • C. Torell
    Torell is a given name and surname of Scandinavian origin, often considered a variant or diminutive of the name Tore.
  • D. Teron
    Teron is one of the traditional clans of the Karbi people, an indigenous ethnic group primarily inhabiting the Karbi Anglong region of Assam in Northeast India.
  • E. Tarak
    Tarak is the popular nickname of N. T. Rama Rao Jr., a leading Telugu film actor known for his roles in action and drama movies.
  • 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_69ca82f2dbe48190aba982e75a0d94de completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb808bc22481909ce2f8b48cc95806 completed March 31, 2026, 8:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc78c0c208190ba590c74512a4043 completed April 2, 2026, 1:34 a.m.
NEDg Description generation batch_69cdcc88456c8190ba8613b4cbf40fbb completed April 2, 2026, 1:55 a.m.
NED2 Entity disambiguation (via description) batch_69cdcd75714881908f0b069a94ee334f completed April 2, 2026, 1:59 a.m.
Created at: March 30, 2026, 6 p.m.