Triple

T36624710

Position	Surface form	Disambiguated ID	Type / Status
Subject	Dham River	`E904138`	entity
Predicate	nameInMarathiScript	`P36892`	FINISHED
Object	धाम नदी धाम नदी मध्य भारतातील एक लहान पण महत्त्वाची नदी आहे जी स्थानिक शेती आणि पाणीपुरवठ्यास हातभार लावते.	`E2273470`	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: धाम नदी | Statement: [Dham River, nameInMarathiScript, धाम नदी]

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: धाम नदी
Triple: [Dham River, nameInMarathiScript, धाम नदी]

Generated description

धाम नदी मध्य भारतातील एक लहान पण महत्त्वाची नदी आहे जी स्थानिक शेती आणि पाणीपुरवठ्यास हातभार लावते.

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

Target predicate: nameInMarathiScript
Context triple: [Dham River, nameInMarathiScript, धाम नदी]

A. nameInDevanagari chosen
Indicates that an entity’s name is written or represented using the Devanagari script.
B. nameInHindi
Indicates that one entity is the Hindi-language name or label corresponding to another entity.
C. nameInSanskrit
Indicates that one entity is the name or designation of another entity when expressed in the Sanskrit language.
D. nameInMeiteiScript
Indicates that an entity’s name is written or represented in the Meitei (Meetei Mayek) script.
E. nameInKannada
Indicates that one entity is the name or label of another entity expressed specifically in the Kannada language.
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_69f76e6ae750819096911e6e2d4d12c5`	completed	May 3, 2026, 3:48 p.m.
NER	Named-entity recognition	`batch_69f7c9f5a8848190ba956ff27f44e396`	completed	May 3, 2026, 10:19 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a41d631c2548190a021564b99378840`	completed	June 29, 2026, 2:19 a.m.
NEDg	Description generation	`batch_6a41da547e2481909ccd8b5698a5f78e`	completed	June 29, 2026, 2:37 a.m.
NED2	Entity disambiguation (via description)	`batch_6a41daa4a87c8190b998dadf04640b7c`	completed	June 29, 2026, 2:38 a.m.
PD	Predicate disambiguation	`batch_69f7c8999a348190abc1895eaa6e036d`	completed	May 3, 2026, 10:13 p.m.

Created at: May 3, 2026, 4:11 p.m.