Triple

T13161834
Position Surface form Disambiguated ID Type / Status
Subject Indo-Parthians E312745 entity
Predicate capital P234 FINISHED
Object Sakastan
Sakastan was an ancient historical region in what is now southeastern Iran and surrounding areas, known as a major center of Indo-Iranian and later Indo-Parthian rule.
E1024074 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: Sakastan | Statement: [Indo-Parthians, capital, Sakastan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sakastan
Context triple: [Indo-Parthians, capital, Sakastan]
  • A. Kashirin
    Kashirin is a Russian masculine surname commonly used in Slavic-speaking countries.
  • B. Saratak
    Saratak is a rural village located in Armenia's Shirak Province.
  • C. Rashua
    Rashua is a small volcanic island in Russia’s Kuril Islands chain in the northwest Pacific Ocean.
  • D. Sa’och
    Sa’och is an indigenous Pearic language (and its associated ethnic group) of mainland Southeast Asia, traditionally spoken by a small community in Cambodia and nearby regions.
  • E. Touqan
    Touqan is a family name of notable Palestinian origin, associated with prominent poets, politicians, and intellectuals in the Arab world.
  • 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: Sakastan
Triple: [Indo-Parthians, capital, Sakastan]
Generated description
Sakastan was an ancient historical region in what is now southeastern Iran and surrounding areas, known as a major center of Indo-Iranian and later Indo-Parthian rule.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sakastan
Target entity description: Sakastan was an ancient historical region in what is now southeastern Iran and surrounding areas, known as a major center of Indo-Iranian and later Indo-Parthian rule.
  • A. Kashirin
    Kashirin is a Russian masculine surname commonly used in Slavic-speaking countries.
  • B. Saratak
    Saratak is a rural village located in Armenia's Shirak Province.
  • C. Rashua
    Rashua is a small volcanic island in Russia’s Kuril Islands chain in the northwest Pacific Ocean.
  • D. Sa’och
    Sa’och is an indigenous Pearic language (and its associated ethnic group) of mainland Southeast Asia, traditionally spoken by a small community in Cambodia and nearby regions.
  • E. Touqan
    Touqan is a family name of notable Palestinian origin, associated with prominent poets, politicians, and intellectuals in the Arab world.
  • 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_69d806ac3ee081909b2fd27d060aa974 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c0a9d348190909fcf45f9d650e4 completed April 10, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eaf4cd788190b74cca51b5219bfb completed May 3, 2026, 6:28 a.m.
NEDg Description generation batch_69f6eeefa9a08190b042212f24735ca7 completed May 3, 2026, 6:45 a.m.
NED2 Entity disambiguation (via description) batch_69f6ef933f888190880e680f7f4c1c29 completed May 3, 2026, 6:47 a.m.
Created at: April 9, 2026, 9:12 p.m.