Triple

T8031978
Position Surface form Disambiguated ID Type / Status
Subject Gan E187005 entity
Predicate relatedTo P37 FINISHED
Object Gan Chinese E181409 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: Gan Chinese | Statement: [Gan, relatedTo, Gan Chinese]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gan Chinese
Context triple: [Gan, relatedTo, Gan Chinese]
  • A. Gan Chinese chosen
    Gan Chinese is a major Sinitic language variety spoken primarily in Jiangxi province and surrounding regions in southeastern China.
  • B. Xiang Chinese
    Xiang Chinese is a major Sinitic language variety spoken primarily in Hunan province and surrounding regions in south-central China.
  • C. Jin Chinese
    Jin Chinese is a major Sinitic language variety spoken primarily in Shanxi and surrounding regions of northern China, often considered distinct from standard Mandarin due to its unique phonological and lexical features.
  • D. Wu Chinese
    Wu Chinese is a major Sinitic language group spoken primarily in Shanghai, southern Jiangsu, and Zhejiang, known for its rich tonal system and significant phonological differences from Mandarin.
  • E. Zhong Wen
    Zhong Wen is the tough, determined police officer portrayed by Jackie Chan in the action film "Police Story 2013."
  • 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_69ca82ae2d1081909dbfee42b41db419 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3ef18da48190835454a5eb969da7 completed March 31, 2026, 3:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc56e812dc81908916fc7163ae344a completed March 31, 2026, 11:21 p.m.
Created at: March 30, 2026, 5:22 p.m.