Triple

T302150
Position Surface form Disambiguated ID Type / Status
Subject Romani language E6220 entity
Predicate languageFamilyBranch P1967 FINISHED
Object Central Indo-Aryan E7769 NE FINISHED

How this triple was built (3 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: Central Indo-Aryan | Statement: [Romani language, languageFamilyBranch, Central Indo-Aryan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Central Indo-Aryan
Context triple: [Romani language, languageFamilyBranch, Central Indo-Aryan]
  • A. Indo-Aryan languages chosen
    Indo-Aryan languages are a major branch of the Indo-European family spoken primarily in the Indian subcontinent, including languages such as Hindi, Bengali, Punjabi, and Marathi.
  • B. Indo-Iranian languages
    Indo-Iranian languages are a major branch of the Indo-European language family that includes numerous related languages spoken across Iran, Afghanistan, the Indian subcontinent, and surrounding regions.
  • C. South-Central Dravidian
    South-Central Dravidian is a branch of the Dravidian language family that includes languages such as Telugu and related tongues spoken primarily in south-central India.
  • D. Indo-Europeans
    Indo-Europeans were a Eurasian people speaking Indo-European languages whose migrations and cultural expansions gave rise to many of the major linguistic and ethnic groups across Europe and parts of Asia.
  • E. Dravidian languages
    Dravidian languages are a family of languages primarily spoken in South India and parts of Sri Lanka, including major languages such as Tamil, Telugu, Kannada, and Malayalam.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: languageFamilyBranch
Context triple: [Romani language, languageFamilyBranch, Central Indo-Aryan]
  • A. languageFamily
    Indicates that two or more languages belong to the same genealogical language family or linguistic lineage.
  • B. languageOfFamily
    Indicates the language or languages commonly used or associated with a particular family.
  • C. languageFamilyCode
    Indicates the language family to which a given language belongs, represented by a standardized code.
  • D. languageBranch chosen
    Indicates that one language belongs to, or is classified under, a broader linguistic branch or subgroup.
  • E. languageFamilyStatus
    Indicates the classification or recognition status of a language within a particular language family (e.g., primary, branch, extinct, or disputed).
  • F. None of above.

Provenance (4 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_69a2e79230508190b912ecb555aae17e completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2ea2fba548190a5aeb1597dca96bd completed Feb. 28, 2026, 1:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3aba2b38c8190b841014b24e14822 completed March 1, 2026, 2:59 a.m.
PD Predicate disambiguation batch_69a2e93c367881908d3f6e2b81d44d7f completed Feb. 28, 2026, 1:10 p.m.
Created at: Feb. 28, 2026, 1:06 p.m.