Triple

T11220129
Position Surface form Disambiguated ID Type / Status
Subject Bai Chongxi E265537 entity
Predicate familyName P18 FINISHED
Object Bai E193112 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: Bai | Statement: [Bai Chongxi, familyName, Bai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bai
Context triple: [Bai Chongxi, familyName, Bai]
  • A. Bai chosen
    The Bai are an ethnic minority group in China known for their distinct language, traditional architecture, and rich cultural heritage centered around the Dali region of Yunnan.
  • B. Baidima
    Baidima is a traditional folk dance of the Dimasa people of Northeast India, performed during cultural and festive occasions to express joy and community identity.
  • C. Bao Si
    Bao Si was a famed beauty of ancient China whose relationship with King You of Zhou is often blamed in legend for contributing to the downfall of the Western Zhou dynasty.
  • D. Baij
    Baij is the surname of Ramkinkar Baij, a pioneering Indian modernist sculptor and painter known for his monumental public works and experimental style.
  • E. Dai
    Dai is a common Welsh given name, often used as a familiar or diminutive form of David.
  • 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_69d6aac59460819089b9848b27f57848 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8eb84c48190b4f3bede254afde2 completed April 9, 2026, 5:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4976f38788190855aed6338d819b7 completed April 19, 2026, 8:50 a.m.
Created at: April 8, 2026, 9:30 p.m.