Triple

T17024353
Position Surface form Disambiguated ID Type / Status
Subject Project A E413024 entity
Predicate stars P1956 FINISHED
Object Dick Wei
Dick Wei is a Taiwanese martial artist and actor best known for playing formidable villains in 1980s Hong Kong action films.
E1245665 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: Dick Wei | Statement: [Project A, stars, Dick Wei]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dick Wei
Context triple: [Project A, stars, Dick Wei]
  • A. Jeff Wu
    Jeff Wu is a machine learning researcher known for his work on large language models, including co-authoring the original GPT-2 paper at OpenAI.
  • B. John Cheng
    John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • C. Joseph Wu
    Joseph Wu is a Taiwanese politician and diplomat who has served in key roles managing Taiwan’s relations with China and its broader foreign affairs.
  • D. Johnny Chiang
    Johnny Chiang is a Taiwanese politician who has served as a prominent leader within the Kuomintang (KMT) party and as a legislator in Taiwan’s Legislative Yuan.
  • E. Jim Cheung
    Jim Cheung is a British comic book artist best known for his detailed, dynamic work on major Marvel titles such as Young Avengers and various large-scale crossover events.
  • 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: Dick Wei
Triple: [Project A, stars, Dick Wei]
Generated description
Dick Wei is a Taiwanese martial artist and actor best known for playing formidable villains in 1980s Hong Kong action films.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dick Wei
Target entity description: Dick Wei is a Taiwanese martial artist and actor best known for playing formidable villains in 1980s Hong Kong action films.
  • A. Jeff Wu
    Jeff Wu is a machine learning researcher known for his work on large language models, including co-authoring the original GPT-2 paper at OpenAI.
  • B. John Cheng
    John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • C. Joseph Wu
    Joseph Wu is a Taiwanese politician and diplomat who has served in key roles managing Taiwan’s relations with China and its broader foreign affairs.
  • D. Johnny Chiang
    Johnny Chiang is a Taiwanese politician who has served as a prominent leader within the Kuomintang (KMT) party and as a legislator in Taiwan’s Legislative Yuan.
  • E. Jim Cheung
    Jim Cheung is a British comic book artist best known for his detailed, dynamic work on major Marvel titles such as Young Avengers and various large-scale crossover events.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d5d371148190a60d32a72abec09a completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b514de481909c78c17a3014b468 completed May 10, 2026, 11:57 p.m.
NEDg Description generation batch_6a011c021e1c819098e04b1cbaf33ecd completed May 11, 2026, midnight
NED2 Entity disambiguation (via description) batch_6a011c8afb608190b51c7a4c9ccaa0a5 completed May 11, 2026, 12:02 a.m.
Created at: April 10, 2026, 5:33 a.m.