Triple

T7309177
Position Surface form Disambiguated ID Type / Status
Subject Harappa E168047 entity
Predicate hasWritingSystem P454 FINISHED
Object Indus script E169855 NE FINISHED

How this triple was built (2 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: Indus script | Statement: [Harappa, hasWritingSystem, Indus script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Indus script
Context triple: [Harappa, hasWritingSystem, Indus script]
  • A. Indus script chosen
    The Indus script is an undeciphered system of symbols used by the ancient Indus Valley Civilization, known from short inscriptions on seals, tablets, and pottery dating to around 2600–1900 BCE.
  • B. Prachalit script
    Prachalit script is a historical Brahmic writing system used primarily for the Nepal Bhasa (Newar) language of the Kathmandu Valley.
  • C. Brahmi script
    The Brahmi script is one of the oldest writing systems of the Indian subcontinent, serving as the ancestor of most modern South and Southeast Asian scripts.
  • D. Kharoṣṭhī script
    The Kharoṣṭhī script is an ancient right-to-left writing system used in northwestern South Asia, especially in the Gandhāra region, primarily for early Buddhist and administrative texts.
  • E. Tirhuta script
    Tirhuta script is a traditional Brahmic writing system historically used for the Maithili language of the Mithila region in India and Nepal.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c6888d8e3c81909db79714903baf31 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6ebda7b748190a230a22ecea79342 completed March 27, 2026, 8:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7e567df3c8190a1baaa7ef9c99d87 completed March 28, 2026, 2:27 p.m.
Created at: March 27, 2026, 3:01 p.m.