Triple

T22033087
Position Surface form Disambiguated ID Type / Status
Subject Hsu Li-kong E544132 entity
Predicate givenName P17 FINISHED
Object Li-kong
Li-kong is the given name of Hsu Li-kong, a Taiwanese film producer known for his work on internationally acclaimed movies.
 E1515453 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: Li-kong | Statement: [Hsu Li-kong, givenName, Li-kong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Li-kong
Context triple: [Hsu Li-kong, givenName, Li-kong]
  • A. Kong Li
    Kong Li was an ancient Chinese figure known primarily as the son of Confucius’s grandson Kong Ji, belonging to the direct lineage of Confucius.
  • B. Lin Kong
    Lin Kong is an actor best known for his role in the acclaimed Chinese film "Raise the Red Lantern."
  • C. Kong Lin
    Kong Lin is the historic family cemetery of Confucius and his descendants in Qufu, Shandong, and a major Confucian cultural heritage site in China.
  • D. Kong He
    Kong He was the father of the ancient Chinese philosopher Confucius and a minor aristocratic military officer in the state of Lu.
  • E. Lin Sen
    Lin Sen was a Chinese politician who served as the chairman of the National Government of the Republic of China during the turbulent years leading up to and including much of the Second Sino-Japanese War.
  • 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: Li-kong
Triple: [Hsu Li-kong, givenName, Li-kong]
Generated description
Li-kong is the given name of Hsu Li-kong, a Taiwanese film producer known for his work on internationally acclaimed movies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Li-kong
Target entity description: Li-kong is the given name of Hsu Li-kong, a Taiwanese film producer known for his work on internationally acclaimed movies.
  • A. Kong Li
    Kong Li was an ancient Chinese figure known primarily as the son of Confucius’s grandson Kong Ji, belonging to the direct lineage of Confucius.
  • B. Lin Kong
    Lin Kong is an actor best known for his role in the acclaimed Chinese film "Raise the Red Lantern."
  • C. Kong Lin
    Kong Lin is the historic family cemetery of Confucius and his descendants in Qufu, Shandong, and a major Confucian cultural heritage site in China.
  • D. Kong He
    Kong He was the father of the ancient Chinese philosopher Confucius and a minor aristocratic military officer in the state of Lu.
  • E. Lin Sen
    Lin Sen was a Chinese politician who served as the chairman of the National Government of the Republic of China during the turbulent years leading up to and including much of the Second Sino-Japanese War.
  • 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_69e11e2f98c8819083e11eab90942a78 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127ee84848190a22c24bf14498520 completed April 28, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a7b69b60881908bcd9e4b45bef76a completed May 18, 2026, 2:37 a.m.
NEDg Description generation batch_6a0a7cc28f4c819090f937449dde8a64 completed May 18, 2026, 2:43 a.m.
NED2 Entity disambiguation (via description) batch_6a0a7d29f5a08190b41cad11e2192727 completed May 18, 2026, 2:44 a.m.
Created at: April 16, 2026, 8:24 p.m.