Triple

T2312085
Position Surface form Disambiguated ID Type / Status
Subject Peng E51981 entity
Predicate hasVariantTransliteration P5923 FINISHED
Object Pang
Pang is a variant transliteration of the Chinese surname commonly romanized as Peng.
 E257324 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: Pang | Statement: [Peng, hasVariantTransliteration, Pang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pang
Context triple: [Peng, hasVariantTransliteration, Pang]
  • A. Poh Pitu
    Poh Pitu was an early capital city of the Medang Kingdom, an ancient Javanese Hindu-Buddhist polity in what is now Indonesia.
  • B. Pénjamo
    Pénjamo is a historic town in the Mexican state of Guanajuato, best known as the birthplace of independence leader Miguel Hidalgo y Costilla.
  • C. Peren
    Peren is a town and administrative center in the northeastern Indian state of Nagaland.
  • D. Punakapina
    Punakapina is the Finnish Civil War of 1918, a conflict between the socialist Reds and conservative Whites that shaped Finland’s early independence.
  • E. Ronga
    Ronga is a Bantu language spoken primarily in southern Mozambique, known for contributing vocabulary and structural features to African varieties of Portuguese.
  • 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: Pang
Triple: [Peng, hasVariantTransliteration, Pang]
Generated description
Pang is a variant transliteration of the Chinese surname commonly romanized as Peng.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pang
Target entity description: Pang is a variant transliteration of the Chinese surname commonly romanized as Peng.
  • A. Poh Pitu
    Poh Pitu was an early capital city of the Medang Kingdom, an ancient Javanese Hindu-Buddhist polity in what is now Indonesia.
  • B. Pénjamo
    Pénjamo is a historic town in the Mexican state of Guanajuato, best known as the birthplace of independence leader Miguel Hidalgo y Costilla.
  • C. Peren
    Peren is a town and administrative center in the northeastern Indian state of Nagaland.
  • D. Punakapina
    Punakapina is the Finnish Civil War of 1918, a conflict between the socialist Reds and conservative Whites that shaped Finland’s early independence.
  • E. Ronga
    Ronga is a Bantu language spoken primarily in southern Mozambique, known for contributing vocabulary and structural features to African varieties of Portuguese.
  • 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_69a88b0bb30c81908ded03b006d29387 completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abc61a8e248190b5024cca9efd806d completed March 7, 2026, 6:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae960dfb708190868126460d27b144 completed March 9, 2026, 9:42 a.m.
NEDg Description generation batch_69ae96ea1b6c81908e05ca78c5e07320 completed March 9, 2026, 9:46 a.m.
NED2 Entity disambiguation (via description) batch_69ae97a775008190bdda2f63810cd5e8 completed March 9, 2026, 9:49 a.m.
Created at: March 4, 2026, 7:49 p.m.