Triple

T9125067
Position Surface form Disambiguated ID Type / Status
Subject Bama E218949 entity
Predicate traditionalDress P5541 FINISHED
Object longyi E670770 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: longyi | Statement: [Bama, traditionalDress, longyi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: longyi
Context triple: [Bama, traditionalDress, longyi]
  • A. longyi chosen
    A longyi is a cylindrical piece of cloth worn as a skirt-like garment by people in Myanmar, commonly used by both men and women in everyday life and on formal occasions.
  • B. Longgu
    Longgu is an Oceanic Austronesian language spoken in the Solomon Islands, known for its complex verbal morphology and rich system of possessive constructions.
  • C. Yonglian
    Yonglian was the first son and briefly designated heir of the Qianlong Emperor of the Qing dynasty, whose early death deeply affected his father and altered the imperial succession.
  • D. Liulichang
    Liulichang is a famous historic cultural street in Beijing known for its traditional architecture, antique shops, and stores selling calligraphy, paintings, and rare books.
  • E. Yangluo
    Yangluo is a town in Wuhan, Hubei Province, China, known as an industrial and port area along the Yangtze River.
  • 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_69ca83dddd548190983b96c664f7f367 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca8b7436c8190b45bc6e4d6ec7066 completed April 1, 2026, 5:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d030988a888190b5a1e4fd6bd7fcee completed April 3, 2026, 9:26 p.m.
Created at: March 30, 2026, 7:17 p.m.