Triple

T8384994
Position Surface form Disambiguated ID Type / Status
Subject Infernal Affairs E197793 entity
Predicate director P255 FINISHED
Object Alan Mak
Alan Mak is a Hong Kong film director and screenwriter best known for co-directing the acclaimed crime thriller "Infernal Affairs" and its sequels.
 E729996 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: Alan Mak | Statement: [Infernal Affairs, director, Alan Mak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Alan Mak
Context triple: [Infernal Affairs, director, Alan Mak]
  • A. David Mack
    David Mack is an American author best known for his numerous Star Trek tie-in novels and related science fiction works.
  • B. Michael Greenwood
    Michael Greenwood is a member of the Greenwood family, known primarily as a son of British politician Hamar Greenwood, 1st Viscount Greenwood.
  • C. Mark Sanger
    Mark Sanger is a British film editor best known for his Academy Award–winning work on the science fiction thriller "Gravity."
  • D. Alan Ereira
    Alan Ereira is a British historian, broadcaster, and documentary filmmaker known for his work on medieval history and indigenous cultures.
  • E. Phil Johnston
    Phil Johnston is an American screenwriter and filmmaker known for co-writing animated hits such as Disney's "Zootopia" and "Wreck-It Ralph."
  • 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: Alan Mak
Triple: [Infernal Affairs, director, Alan Mak]
Generated description
Alan Mak is a Hong Kong film director and screenwriter best known for co-directing the acclaimed crime thriller "Infernal Affairs" and its sequels.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Alan Mak
Target entity description: Alan Mak is a Hong Kong film director and screenwriter best known for co-directing the acclaimed crime thriller "Infernal Affairs" and its sequels.
  • A. David Mack
    David Mack is an American author best known for his numerous Star Trek tie-in novels and related science fiction works.
  • B. Michael Greenwood
    Michael Greenwood is a member of the Greenwood family, known primarily as a son of British politician Hamar Greenwood, 1st Viscount Greenwood.
  • C. Mark Sanger
    Mark Sanger is a British film editor best known for his Academy Award–winning work on the science fiction thriller "Gravity."
  • D. Alan Ereira
    Alan Ereira is a British historian, broadcaster, and documentary filmmaker known for his work on medieval history and indigenous cultures.
  • E. Phil Johnston
    Phil Johnston is an American screenwriter and filmmaker known for co-writing animated hits such as Disney's "Zootopia" and "Wreck-It Ralph."
  • 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_69ca82f749388190bffbea6dfb509016 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb80e03eb08190a458c9caa0524e0f completed March 31, 2026, 8:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde8312be48190bd5896adc8bb4e95 completed April 2, 2026, 3:53 a.m.
NEDg Description generation batch_69cdebfafe84819097f387318897dae1 completed April 2, 2026, 4:09 a.m.
NED2 Entity disambiguation (via description) batch_69cded2a9c2c8190bdbeddad562ef9e8 completed April 2, 2026, 4:14 a.m.
Created at: March 30, 2026, 6:02 p.m.