Triple

T17025833
Position Surface form Disambiguated ID Type / Status
Subject Pedicab Driver E413060 entity
Predicate starring P1507 FINISHED
Object Mang Hoi
Mang Hoi is a Hong Kong actor and action choreographer known for his roles in martial arts and action films, particularly during the 1980s.
E1246444 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: Mang Hoi | Statement: [Pedicab Driver, starring, Mang Hoi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mang Hoi
Context triple: [Pedicab Driver, starring, Mang Hoi]
  • A. Cua Lo
    Cua Lo is a coastal town in north-central Vietnam known for its long sandy beaches and role as a popular seaside tourist destination.
  • B. Mangseng
    Mangseng is an Oceanic language spoken in parts of western Melanesia, belonging to the Western Oceanic branch of the Austronesian language family.
  • C. Boi-ngo
    Boi-ngo is a 1987 studio album by American new wave band Oingo Boingo, showcasing their blend of rock, ska, and quirky, theatrical pop.
  • D. Se Kong
    Se Kong is a major river in Southeast Asia that flows through Laos, Vietnam, and Cambodia before joining the Mekong River.
  • E. Singa
    Singa is a city in southeastern Sudan that serves as the administrative and economic center of Sennar State along the Blue Nile.
  • 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: Mang Hoi
Triple: [Pedicab Driver, starring, Mang Hoi]
Generated description
Mang Hoi is a Hong Kong actor and action choreographer known for his roles in martial arts and action films, particularly during the 1980s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mang Hoi
Target entity description: Mang Hoi is a Hong Kong actor and action choreographer known for his roles in martial arts and action films, particularly during the 1980s.
  • A. Cua Lo
    Cua Lo is a coastal town in north-central Vietnam known for its long sandy beaches and role as a popular seaside tourist destination.
  • B. Mangseng
    Mangseng is an Oceanic language spoken in parts of western Melanesia, belonging to the Western Oceanic branch of the Austronesian language family.
  • C. Boi-ngo
    Boi-ngo is a 1987 studio album by American new wave band Oingo Boingo, showcasing their blend of rock, ska, and quirky, theatrical pop.
  • D. Se Kong
    Se Kong is a major river in Southeast Asia that flows through Laos, Vietnam, and Cambodia before joining the Mekong River.
  • E. Singa
    Singa is a city in southeastern Sudan that serves as the administrative and economic center of Sennar State along the Blue Nile.
  • 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_69e3d5d46a5081908bc5681621dd8534 completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b53306081908972a0a5db474b6c completed May 10, 2026, 11:57 p.m.
NEDg Description generation batch_6a011cfb74b88190bbd5af862727790f completed May 11, 2026, 12:04 a.m.
NED2 Entity disambiguation (via description) batch_6a011dad838c8190a1ea560680c9ca57 completed May 11, 2026, 12:07 a.m.
Created at: April 10, 2026, 5:33 a.m.