Triple

T9192926
Position Surface form Disambiguated ID Type / Status
Subject Middle Mon E220632 entity
Predicate region P40 FINISHED
Object Thaton region E276027 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: Thaton region | Statement: [Middle Mon, region, Thaton region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thaton region
Context triple: [Middle Mon, region, Thaton region]
  • A. Thaton chosen
    Thaton is an ancient city in southern Myanmar historically significant as a major center of the Mon kingdom and Theravada Buddhism in the region.
  • B. Nohur region
    The Nohur region is a remote mountainous area in southern Turkmenistan known for its distinct local culture, traditions, and dialect.
  • C. Taunus region
    The Taunus region is a low mountain range in Hesse, Germany, known for its forested hills, spa towns, and historical castles overlooking the Rhine-Main area.
  • D. Saaxil region
    Saaxil region is an administrative region in northwestern Somaliland that includes the strategic coastal area around the Port of Berbera on the Gulf of Aden.
  • E. Maekel Region
    Maekel Region is a central administrative region of Eritrea that includes the nation’s capital, Asmara, and serves as its political and economic hub.
  • 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_69ca83e7ba70819088b74866d9da2c30 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccd5c1fa9c8190bc5cc6dce8778694 completed April 1, 2026, 8:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05c2bb2c481909db8c223aececf37 completed April 4, 2026, 12:32 a.m.
Created at: March 30, 2026, 7:24 p.m.