Triple

T10110012
Position Surface form Disambiguated ID Type / Status
Subject New Xiang E218214 entity
Predicate contrastWith P278 FINISHED
Object Old Xiang E218215 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: Old Xiang | Statement: [New Xiang, contrastWith, Old Xiang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Xiang
Context triple: [New Xiang, contrastWith, Old Xiang]
  • A. Old Xiang chosen
    Old Xiang is a conservative variety of Xiang Chinese that preserves many archaic phonological and lexical features lost in other Xiang dialects.
  • B. Lao An
    Lao An is the wife of former Chinese premier Zhu Rongji and a relatively private figure associated with China's political elite.
  • C. Guan Xing
    Guan Xing was a military officer of the Shu Han state during China’s Three Kingdoms period, best known as one of the sons and successors of the famed general Guan Yu.
  • D. Xiong Lü
    Xiong Lü was the personal name of King Zhuang of Chu, a prominent and powerful monarch of the ancient Chinese state of Chu during the Spring and Autumn period.
  • E. Longhui Xiang
    Longhui Xiang is a regional variety of the Xiang Chinese language spoken in and around Longhui County in Hunan Province, China.
  • 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_69ca83da93fc8190b54e44bc2b34857c completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cdd0cdb3c88190a74f75bf865664f3 completed April 2, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d3005e007881909f40575d129f2c3d completed April 6, 2026, 12:37 a.m.
Created at: March 30, 2026, 9:03 p.m.