Triple

T4459736
Position Surface form Disambiguated ID Type / Status
Subject Special ID E98221 entity
Predicate hasCastMember P2308 FINISHED
Object Andy On
Andy On is a Taiwanese-American actor and martial artist known for his roles in Hong Kong action films such as "Black Mask 2" and "New Police Story."
E443051 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: Andy On | Statement: [Special ID, hasCastMember, Andy On]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andy On
Context triple: [Special ID, hasCastMember, Andy On]
  • A. Andy
    Andy is the central character in the 1991 Australian psychological drama film "Proof," around whom the story’s exploration of trust, perception, and relationships revolves.
  • B. Andy C
    Andy C is a renowned British drum and bass DJ and producer, celebrated for his influential role in shaping the genre and co-founding the RAM Records label.
  • C. Alan
    Alan is a masculine given name of Celtic origin that has been widely used in English-speaking countries.
  • D. Andre
    Andre is the given name of Andre Reed, a former American football wide receiver best known for his long career with the Buffalo Bills in the NFL.
  • E. Ant
    Ant is a Java-based build automation tool commonly used to compile, package, and deploy Java applications using XML configuration files.
  • 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: Andy On
Triple: [Special ID, hasCastMember, Andy On]
Generated description
Andy On is a Taiwanese-American actor and martial artist known for his roles in Hong Kong action films such as "Black Mask 2" and "New Police Story."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Andy On
Target entity description: Andy On is a Taiwanese-American actor and martial artist known for his roles in Hong Kong action films such as "Black Mask 2" and "New Police Story."
  • A. Andy
    Andy is the central character in the 1991 Australian psychological drama film "Proof," around whom the story’s exploration of trust, perception, and relationships revolves.
  • B. Andy C
    Andy C is a renowned British drum and bass DJ and producer, celebrated for his influential role in shaping the genre and co-founding the RAM Records label.
  • C. Alan
    Alan is a masculine given name of Celtic origin that has been widely used in English-speaking countries.
  • D. Andre
    Andre is the given name of Andre Reed, a former American football wide receiver best known for his long career with the Buffalo Bills in the NFL.
  • E. Ant
    Ant is a Java-based build automation tool commonly used to compile, package, and deploy Java applications using XML configuration files.
  • 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_69b3454a7c608190944f5455c8031d73 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3567184f481908a2787e4ac9bb345 completed March 13, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69b6284431c48190aa1553ff89f2239f completed March 15, 2026, 3:32 a.m.
NEDg Description generation batch_69b629532cac8190b959adc0ef13305a completed March 15, 2026, 3:36 a.m.
NED2 Entity disambiguation (via description) batch_69b62d9c287c8190a305f9d21517f913 completed March 15, 2026, 3:55 a.m.
Created at: March 12, 2026, 11:33 p.m.