Triple

T10527673
Position Surface form Disambiguated ID Type / Status
Subject Balls of Fury E248347 entity
Predicate character P662 FINISHED
Object Feng
Feng is the flamboyant and villainous crime lord and ping-pong master who serves as the main antagonist in the comedy film "Balls of Fury."
 E869515 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: Feng | Statement: [Balls of Fury, character, Feng]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Feng
Context triple: [Balls of Fury, character, Feng]
  • A. Feng
    Feng was an early capital city of the Zhou dynasty in ancient China, serving as a key political and cultural center before later relocations.
  • B. Feng
    Feng is a Chinese surname borne by various notable figures in Chinese history and culture.
  • C. Yifeng
    Yifeng was a Chinese era name used during the reign of Emperor Gaozong of the Tang dynasty.
  • D. Shenfeng
    Shenfeng was a historical Chinese era name used during the reign of Sun Quan, ruler of Eastern Wu in the Three Kingdoms period.
  • E. Sulamutag Feng
    Sulamutag Feng is the highest peak in China’s remote Altyn-Tagh mountain range on the northern edge of the Tibetan Plateau.
  • 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: Feng
Triple: [Balls of Fury, character, Feng]
Generated description
Feng is the flamboyant and villainous crime lord and ping-pong master who serves as the main antagonist in the comedy film "Balls of Fury."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Feng
Target entity description: Feng is the flamboyant and villainous crime lord and ping-pong master who serves as the main antagonist in the comedy film "Balls of Fury."
  • A. Feng
    Feng is a Chinese surname borne by various notable figures in Chinese history and culture.
  • B. Feng
    Feng was an early capital city of the Zhou dynasty in ancient China, serving as a key political and cultural center before later relocations.
  • C. Yifeng
    Yifeng was a Chinese era name used during the reign of Emperor Gaozong of the Tang dynasty.
  • D. Shenfeng
    Shenfeng was a historical Chinese era name used during the reign of Sun Quan, ruler of Eastern Wu in the Three Kingdoms period.
  • E. Sulamutag Feng
    Sulamutag Feng is the highest peak in China’s remote Altyn-Tagh mountain range on the northern edge of the Tibetan Plateau.
  • 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_69d381c5c7448190bec34bee7ec72bac completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509f5ec348190875c8c877e70ba4a completed April 7, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90e31350c8190a7493cdc33cc450a completed April 10, 2026, 2:50 p.m.
NEDg Description generation batch_69d9107e8b94819086ebba1675a0db54 completed April 10, 2026, 3 p.m.
NED2 Entity disambiguation (via description) batch_69d911a16b1481909197b00c30de48c4 completed April 10, 2026, 3:05 p.m.
Created at: April 6, 2026, 12:30 p.m.