Triple

T1350784
Position Surface form Disambiguated ID Type / Status
Subject Mayan languages E28875 entity
Predicate hasWritingSystem P454 FINISHED
Object Maya script E153782 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: Maya script | Statement: [Mayan languages, hasWritingSystem, Maya script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maya script
Context triple: [Mayan languages, hasWritingSystem, Maya script]
  • A. Maya script chosen
    Maya script is the complex logosyllabic writing system of the ancient Maya, used to record their history, rituals, astronomy, and royal lineages on monuments, codices, and artifacts.
  • B. Muhaqqaq script
    Muhaqqaq script is a majestic, elongated style of Islamic calligraphy historically favored for large Qur’anic manuscripts and monumental inscriptions.
  • C. RenderMan
    RenderMan is a high-quality 3D rendering software and standard widely used in the film industry for producing photorealistic visual effects and animation.
  • D. Kulitan script
    Kulitan script is an indigenous Philippine writing system traditionally used by the Kapampangan people and now revived as a symbol of their cultural identity.
  • E. Jython
    Jython is an implementation of the Python programming language that runs on the Java platform and allows seamless integration with Java code and libraries.
  • 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_69a498571d248190a0ac9eb02d97097f completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c26981d081909ca3b8d8cdf7cf2e completed March 1, 2026, 10:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69acce6a1dd48190b17ac5a7cf3ab933 completed March 8, 2026, 1:18 a.m.
Created at: March 1, 2026, 7:56 p.m.