Triple

T11528170
Position Surface form Disambiguated ID Type / Status
Subject Bruce Lee E273351 entity
Predicate mother P120 FINISHED
Object Grace Ho
Grace Ho was the mother of martial arts icon Bruce Lee and a member of a prominent Hong Kong family of Eurasian heritage.
E931913 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: Grace Ho | Statement: [Bruce Lee, mother, Grace Ho]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grace Ho
Context triple: [Bruce Lee, mother, Grace Ho]
  • A. Alice Tan
    Alice Tan is one of the namesakes of the College of Alice and Peter Tan at the National University of Singapore, recognized for her contributions alongside Peter Tan.
  • B. Hilary Tsui
    Hilary Tsui is a Hong Kong actress, fashion icon, and designer best known for her work in film and her influential street-style presence in the local fashion scene.
  • C. Michelle Wong
    Michelle Wong is an actress known for her voice role in the animated feature film "Abominable."
  • D. Rachel Fong
    Rachel Fong is a researcher in machine learning and reinforcement learning, known for her work on the Hindsight Experience Replay technique.
  • E. Karen Kwan
    Karen Kwan is an American figure skater and the older sister of Olympic medalist Michelle Kwan.
  • 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: Grace Ho
Triple: [Bruce Lee, mother, Grace Ho]
Generated description
Grace Ho was the mother of martial arts icon Bruce Lee and a member of a prominent Hong Kong family of Eurasian heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Grace Ho
Target entity description: Grace Ho was the mother of martial arts icon Bruce Lee and a member of a prominent Hong Kong family of Eurasian heritage.
  • A. Alice Tan
    Alice Tan is one of the namesakes of the College of Alice and Peter Tan at the National University of Singapore, recognized for her contributions alongside Peter Tan.
  • B. Hilary Tsui
    Hilary Tsui is a Hong Kong actress, fashion icon, and designer best known for her work in film and her influential street-style presence in the local fashion scene.
  • C. Michelle Wong
    Michelle Wong is an actress known for her voice role in the animated feature film "Abominable."
  • D. Rachel Fong
    Rachel Fong is a researcher in machine learning and reinforcement learning, known for her work on the Hindsight Experience Replay technique.
  • E. Karen Kwan
    Karen Kwan is an American figure skater and the older sister of Olympic medalist Michelle Kwan.
  • 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_69d6aae3fbec8190a14632a5df2538b6 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d883972b10819093bd09cf8406671c completed April 10, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6855270b08190bdb175a8dede176e completed April 20, 2026, 7:58 p.m.
NEDg Description generation batch_69e68fd6b6088190b24f552b5afc3f55 completed April 20, 2026, 8:43 p.m.
NED2 Entity disambiguation (via description) batch_69e6b7a31b4081909b06bc9b6d0a1617 completed April 20, 2026, 11:32 p.m.
Created at: April 8, 2026, 9:37 p.m.