Triple

T17111514
Position Surface form Disambiguated ID Type / Status
Subject Tsang E415236 entity
Predicate hasVariantRomanization P5800 FINISHED
Object Zang
Zang is a variant romanization of the Chinese surname commonly spelled Tsang.
E1251109 NE FINISHED

How this triple was built (4 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: Zang | Statement: [Tsang, hasVariantRomanization, Zang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zang
Context triple: [Tsang, hasVariantRomanization, Zang]
  • A. Zanghezur
    Zanghezur is a mountainous region in the South Caucasus, primarily in southern Armenia, known for its rugged terrain, rich mineral resources, and strategic location between Armenia, Azerbaijan, and Iran.
  • B. Zhan
    Zhan is a Chinese surname and given name represented in pinyin, corresponding to one of several Chinese characters and family lineages.
  • C. Zazai
    Zazai is a Pashtun tribe associated with the Karlani tribal confederation, primarily found in eastern Afghanistan and parts of Pakistan.
  • D. Zhaoge
    Zhaoge was an ancient Chinese city that served as the final capital of the Shang dynasty before its fall to the Zhou.
  • E. Renfang
    Renfang was an ancient group or region on the periphery of the Shang dynasty that was the target of King Wu Ding’s military campaigns.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Zang
Triple: [Tsang, hasVariantRomanization, Zang]
Generated description
Zang is a variant romanization of the Chinese surname commonly spelled Tsang.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Zang
Target entity description: Zang is a variant romanization of the Chinese surname commonly spelled Tsang.
  • A. Zanghezur
    Zanghezur is a mountainous region in the South Caucasus, primarily in southern Armenia, known for its rugged terrain, rich mineral resources, and strategic location between Armenia, Azerbaijan, and Iran.
  • B. Zhan
    Zhan is a Chinese surname and given name represented in pinyin, corresponding to one of several Chinese characters and family lineages.
  • C. Zazai
    Zazai is a Pashtun tribe associated with the Karlani tribal confederation, primarily found in eastern Afghanistan and parts of Pakistan.
  • D. Zhaoge
    Zhaoge was an ancient Chinese city that served as the final capital of the Shang dynasty before its fall to the Zhou.
  • E. Renfang
    Renfang was an ancient group or region on the periphery of the Shang dynasty that was the target of King Wu Ding’s military campaigns.
  • F. None of above. chosen

Provenance (5 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_69d886d090cc8190a39cb94992586905 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dc2a7f2c81908eb19594b6accab7 completed April 18, 2026, 7:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a013a062d7c81908fe8cdc9e4637168 completed May 11, 2026, 2:08 a.m.
NEDg Description generation batch_6a013a8e69388190b8d48d70a28e99bd completed May 11, 2026, 2:10 a.m.
NED2 Entity disambiguation (via description) batch_6a013b6824888190853cf36548507e1b completed May 11, 2026, 2:14 a.m.
Created at: April 10, 2026, 5:35 a.m.