Triple

T15902567
Position Surface form Disambiguated ID Type / Status
Subject Rakhine Yoma E385624 entity
Predicate alsoKnownAs P39 FINISHED
Object Arakan Yoma E82024 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: Arakan Yoma | Statement: [Rakhine Yoma, alsoKnownAs, Arakan Yoma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arakan Yoma
Context triple: [Rakhine Yoma, alsoKnownAs, Arakan Yoma]
  • A. Arakan Mountains chosen
    The Arakan Mountains are a rugged coastal mountain range in western Myanmar that form a natural barrier between the country’s central plains and the Bay of Bengal.
  • B. Maung
    Maung is a Burmese surname commonly used in Myanmar and among the Burmese diaspora.
  • C. Maung
    Maung is an Aboriginal Australian language traditionally spoken by the Maung people of the Goulburn Islands in the Northern Territory.
  • D. Tenasserim Hills
    Tenasserim Hills is a long mountain range forming a natural border between Myanmar and Thailand on the Indochinese Peninsula.
  • E. Myanmar Highlands
    The Myanmar Highlands are an extensive mountainous region in eastern Myanmar characterized by rugged terrain, high plateaus, and diverse ethnic communities.
  • 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_69d86da5b800819083a31be937d738b0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1563e79608190a1fdfe6265817616 completed April 16, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5a39a348190a4ef6784c54649c2 completed May 9, 2026, 10:30 p.m.
Created at: April 10, 2026, 4:52 a.m.