Triple

T9889040
Position Surface form Disambiguated ID Type / Status
Subject Gan Chinese E181409 entity
Predicate dialectGroup P1254 FINISHED
Object Fuguang Gan E827486 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: Fuguang Gan | Statement: [Gan Chinese, dialectGroup, Fuguang Gan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fuguang Gan
Context triple: [Gan Chinese, dialectGroup, Fuguang Gan]
  • A. Yiliu Gan chosen
    Yiliu Gan is a regional variety of the Gan branch of Chinese, spoken in a specific area and sharing core features with other Gan dialects while retaining its own local characteristics.
  • B. Fenggang Yang
    Fenggang Yang is a prominent Chinese-American sociologist known for his influential research on religion and religious change in contemporary China.
  • C. Gong Liu
    Gong Liu was an early Zhou dynasty leader credited with consolidating and expanding the Zhou clan, laying foundations for the later rise of the Zhou state in ancient China.
  • D. Guochuan Lai
    Guochuan Lai is a Chinese businessman best known for his ownership of English football club West Bromwich Albion.
  • E. Shaobo Qin
    Shaobo Qin is a Chinese acrobat and actor best known for playing the agile explosives expert Yen in the Ocean's film series.
  • 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_69ca8283a6708190801af7a25a7ebb9f completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cdb47be2988190811a99dc56ae542a completed April 2, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d20d888b408190a68ff55d63558478 completed April 5, 2026, 7:21 a.m.
Created at: March 30, 2026, 8:39 p.m.