Triple

T4755440
Position Surface form Disambiguated ID Type / Status
Subject Samrat Ashok Technological Institute E105575 entity
Predicate shortName P43 FINISHED
Object SATI
SATI is an engineering and technology-focused institute in India formally known as Samrat Ashok Technological Institute.
E467637 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: SATI | Statement: [Samrat Ashok Technological Institute, shortName, SATI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SATI
Context triple: [Samrat Ashok Technological Institute, shortName, SATI]
  • A. satsivi
    Satsivi is a traditional Georgian cold dish of poultry or vegetables served in a rich, spiced walnut sauce.
  • B. SATL
    SATL is the abbreviation for Satakunta Air Command, a unit of the Finnish Air Force responsible for air operations and training.
  • C. Thali
    Thali is a dialect of the Lahnda (Western Punjabi) language spoken primarily in parts of Pakistan’s Punjab region.
  • D. SUT
    SUT is the commonly used abbreviation for Sharif University of Technology, a leading science and engineering university in Iran.
  • E. Suhita
    Suhita was a 15th-century queen and ruler of the Majapahit Empire in Java, known for being one of the few female monarchs in Javanese history.
  • 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: SATI
Triple: [Samrat Ashok Technological Institute, shortName, SATI]
Generated description
SATI is an engineering and technology-focused institute in India formally known as Samrat Ashok Technological Institute.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SATI
Target entity description: SATI is an engineering and technology-focused institute in India formally known as Samrat Ashok Technological Institute.
  • A. satsivi
    Satsivi is a traditional Georgian cold dish of poultry or vegetables served in a rich, spiced walnut sauce.
  • B. SATL
    SATL is the abbreviation for Satakunta Air Command, a unit of the Finnish Air Force responsible for air operations and training.
  • C. Thali
    Thali is a dialect of the Lahnda (Western Punjabi) language spoken primarily in parts of Pakistan’s Punjab region.
  • D. SUT
    SUT is the commonly used abbreviation for Sharif University of Technology, a leading science and engineering university in Iran.
  • E. Suhita
    Suhita was a 15th-century queen and ruler of the Majapahit Empire in Java, known for being one of the few female monarchs in Javanese history.
  • 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_69bd43f07fa48190954317d01600994a completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd64e9d80c819088532921a46ea1d6 completed March 20, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69be3a6c7f3c8190b97705bd859c82e8 completed March 21, 2026, 6:27 a.m.
NEDg Description generation batch_69be3d444b888190b2df7433502604ff completed March 21, 2026, 6:40 a.m.
NED2 Entity disambiguation (via description) batch_69be3dd31c648190bfdac15fb85cfec9 completed March 21, 2026, 6:42 a.m.
Created at: March 20, 2026, 1:20 p.m.