Triple

T36687894

Position	Surface form	Disambiguated ID	Type / Status
Subject	Megha Dootha (Kannada translation)	`E905871`	entity
Predicate	hasTitleInKannadaScript	`P97664`	FINISHED
Object	ಮೇಘ ದೂತ ಮೇಘ ದೂತ is the Kannada translation of Kalidasa’s classical Sanskrit lyrical poem “Meghaduta,” which tells the story of a lovelorn yaksha sending a message to his distant wife through a passing cloud.	`E2194353`	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: ಮೇಘ ದೂತ | Statement: [Megha Dootha (Kannada translation), hasTitleInKannadaScript, ಮೇಘ ದೂತ]

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: ಮೇಘ ದೂತ
Triple: [Megha Dootha (Kannada translation), hasTitleInKannadaScript, ಮೇಘ ದೂತ]

Generated description

ಮೇಘ ದೂತ is the Kannada translation of Kalidasa’s classical Sanskrit lyrical poem “Meghaduta,” which tells the story of a lovelorn yaksha sending a message to his distant wife through a passing cloud.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: hasTitleInKannadaScript
Context triple: [Megha Dootha (Kannada translation), hasTitleInKannadaScript, ಮೇಘ ದೂತ]

A. titleInKannadaScript chosen
Indicates that the title of an entity is written or represented in the Kannada script.
B. titleInSanskritScript
Indicates that the title of an entity is expressed using the Sanskrit writing system.
C. hasTitleInTransliteration
Indicates that an entity has a specific title represented in a transliterated form from another writing system.
D. hasTitleIn
Indicates that an entity holds or is associated with a specific title within a particular context, domain, or language.
E. hasTitleInScript
Indicates that an entity holds a specific title or name as written in a particular script or writing system.
F. None of above.

Provenance (6 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_69f76e70d2448190bdd3ce781ba971c5`	completed	May 3, 2026, 3:49 p.m.
NER	Named-entity recognition	`batch_69fe21b0cba48190b56c39e9f1c0eafa`	completed	May 8, 2026, 5:47 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a3a20e71dbc81909e213f1a3dc82803`	completed	June 23, 2026, 6 a.m.
NEDg	Description generation	`batch_6a3a21fb6a2c8190b554fa1a6d7a28c2`	completed	June 23, 2026, 6:04 a.m.
NED2	Entity disambiguation (via description)	`batch_6a3a2301ed048190826eaba7cfba00ed`	completed	June 23, 2026, 6:09 a.m.
PD	Predicate disambiguation	`batch_69fe204576848190aecf204e2adba5dc`	completed	May 8, 2026, 5:41 p.m.

Created at: May 3, 2026, 4:12 p.m.