Triple

T29540205

Position	Surface form	Disambiguated ID	Type / Status
Subject	Mahendravarman I	`E749470`	entity
Predicate	issuedInscriptions	`P94398`	FINISHED
Object	Mandagapattu inscription The Mandagapattu inscription is an early 7th-century Pallava stone record famed for proclaiming one of the first rock-cut temples in South India, dedicated to Brahma, Vishnu, and Shiva without the use of brick, timber, metal, or mortar.	`E1871579`	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: Mandagapattu inscription | Statement: [Mahendravarman I, issuedInscriptions, Mandagapattu inscription]

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: Mandagapattu inscription
Triple: [Mahendravarman I, issuedInscriptions, Mandagapattu inscription]

Generated description

The Mandagapattu inscription is an early 7th-century Pallava stone record famed for proclaiming one of the first rock-cut temples in South India, dedicated to Brahma, Vishnu, and Shiva without the use of brick, timber, metal, or mortar.

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

Target predicate: issuedInscriptions
Context triple: [Mahendravarman I, issuedInscriptions, Mandagapattu inscription]

A. issuedInscriptionsIn
Indicates that an entity (such as an authority or issuer) produced or authorized inscriptions within a specified place or context.
B. issuedInscription chosen
Indicates that an authority or source formally created and released a specific inscription or written record.
C. hasInscriptions
Indicates that an object, surface, or artifact bears written, carved, or engraved inscriptions on it.
D. numberOfInscriptions
Indicates the total count of inscriptions associated with a given entity or object.
E. isInscribedOn
Indicates that text, symbols, or markings are written, carved, or otherwise permanently placed onto the surface of an object.
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_69f0bd47abb081909bd6e6a33d770fd8`	completed	April 28, 2026, 1:59 p.m.
NER	Named-entity recognition	`batch_69f6c1265c208190aacd2b551f8f0f82`	completed	May 3, 2026, 3:29 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a260c3d35048190a2937d4cd22f268b`	completed	June 8, 2026, 12:26 a.m.
NEDg	Description generation	`batch_6a26108e78fc8190b35e3ec5df7b0c8a`	completed	June 8, 2026, 12:45 a.m.
NED2	Entity disambiguation (via description)	`batch_6a2614d0e1c08190b057693cf0a339de`	completed	June 8, 2026, 1:03 a.m.
PD	Predicate disambiguation	`batch_69f6bd2415fc81908c23c311aebce66f`	completed	May 3, 2026, 3:12 a.m.

Created at: April 28, 2026, 5:02 p.m.