Triple

T4140708
Position Surface form Disambiguated ID Type / Status
Subject Deccan College E89264 entity
Predicate hasDepartment P35 FINISHED
Object Department of Linguistics
The Department of Linguistics at Deccan College is an academic unit dedicated to the scientific study of language, including its structure, history, and use.
E415752 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: Department of Linguistics | Statement: [Deccan College, hasDepartment, Department of Linguistics]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Department of Linguistics
Context triple: [Deccan College, hasDepartment, Department of Linguistics]
  • A. Department of Linguistics
    The Department of Linguistics is an academic unit at the University of Chile dedicated to the scientific study of language, including its structure, use, and development.
  • B. Department of Languages, Literatures & Linguistics
    The Department of Languages, Literatures & Linguistics is an academic unit that focuses on the study and teaching of languages, their literary traditions, and the scientific analysis of language structure and use.
  • C. Department of Language and Literature
    The Department of Language and Literature is a scholarly division of the Serbian Academy of Sciences and Arts dedicated to research, preservation, and advancement of Serbian and other languages and their literary traditions.
  • D. Stanford University Department of Linguistics
    The Stanford University Department of Linguistics is a leading academic department renowned for its research and teaching across theoretical, computational, and sociolinguistics.
  • E. University of Pennsylvania Department of Linguistics
    The University of Pennsylvania Department of Linguistics is a leading academic center for theoretical and empirical linguistics research and education, known for its influential contributions to syntax, phonology, sociolinguistics, and computational linguistics.
  • 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: Department of Linguistics
Triple: [Deccan College, hasDepartment, Department of Linguistics]
Generated description
The Department of Linguistics at Deccan College is an academic unit dedicated to the scientific study of language, including its structure, history, and use.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Department of Linguistics
Target entity description: The Department of Linguistics at Deccan College is an academic unit dedicated to the scientific study of language, including its structure, history, and use.
  • A. Department of Linguistics
    The Department of Linguistics is an academic unit at the University of Chile dedicated to the scientific study of language, including its structure, use, and development.
  • B. Department of Languages, Literatures & Linguistics
    The Department of Languages, Literatures & Linguistics is an academic unit that focuses on the study and teaching of languages, their literary traditions, and the scientific analysis of language structure and use.
  • C. Department of Language and Literature
    The Department of Language and Literature is a scholarly division of the Serbian Academy of Sciences and Arts dedicated to research, preservation, and advancement of Serbian and other languages and their literary traditions.
  • D. Stanford University Department of Linguistics
    The Stanford University Department of Linguistics is a leading academic department renowned for its research and teaching across theoretical, computational, and sociolinguistics.
  • E. University of Pennsylvania Department of Linguistics
    The University of Pennsylvania Department of Linguistics is a leading academic center for theoretical and empirical linguistics research and education, known for its influential contributions to syntax, phonology, sociolinguistics, and computational linguistics.
  • 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_69aed95785788190ae75bcf0cd1cafdf completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af0249dd988190bf6826a744e7771f completed March 9, 2026, 5:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69b576ccdf348190a80305485bee354e completed March 14, 2026, 2:55 p.m.
NEDg Description generation batch_69b577785cdc8190ad0864d63aadf908 completed March 14, 2026, 2:58 p.m.
NED2 Entity disambiguation (via description) batch_69b578168ecc8190bc47f0902b130c7d completed March 14, 2026, 3 p.m.
Created at: March 9, 2026, 3:43 p.m.