Triple

T20772304
Position Surface form Disambiguated ID Type / Status
Subject Leigh Leopards E511265 entity
Predicate coach P2169 FINISHED
Object Adrian Lam
Adrian Lam is a Papua New Guinean former rugby league halfback who became a successful professional coach in the English and Australian competitions.
E1450138 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: Adrian Lam | Statement: [Leigh Leopards, coach, Adrian Lam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adrian Lam
Context triple: [Leigh Leopards, coach, Adrian Lam]
  • A. Joseph Koo
    Joseph Koo was a pioneering Hong Kong composer and songwriter renowned for his influential film scores and Cantopop television theme songs.
  • B. Chan Kin-man
    Chan Kin-man is a Hong Kong sociologist and prominent pro-democracy activist best known as one of the co-founders of the 2014 Umbrella Movement.
  • C. Lawrence Chu
    Lawrence Chu is a Chinese-American chef and restaurateur best known as the father of film director Jon M. Chu.
  • D. Michael Hing
    Michael Hing is an Australian comedian, actor, and broadcaster known for his stand-up, television appearances, and radio work.
  • E. Eddy Choong
    Eddy Choong was a legendary Malaysian badminton player renowned for his multiple All England titles in the 1950s and his pioneering role in the sport’s international rise.
  • 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: Adrian Lam
Triple: [Leigh Leopards, coach, Adrian Lam]
Generated description
Adrian Lam is a Papua New Guinean former rugby league halfback who became a successful professional coach in the English and Australian competitions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Adrian Lam
Target entity description: Adrian Lam is a Papua New Guinean former rugby league halfback who became a successful professional coach in the English and Australian competitions.
  • A. Joseph Koo
    Joseph Koo was a pioneering Hong Kong composer and songwriter renowned for his influential film scores and Cantopop television theme songs.
  • B. Chan Kin-man
    Chan Kin-man is a Hong Kong sociologist and prominent pro-democracy activist best known as one of the co-founders of the 2014 Umbrella Movement.
  • C. Lawrence Chu
    Lawrence Chu is a Chinese-American chef and restaurateur best known as the father of film director Jon M. Chu.
  • D. Michael Hing
    Michael Hing is an Australian comedian, actor, and broadcaster known for his stand-up, television appearances, and radio work.
  • E. Eddy Choong
    Eddy Choong was a legendary Malaysian badminton player renowned for his multiple All England titles in the 1950s and his pioneering role in the sport’s international rise.
  • 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2681ff88190bfe5938c2db6b2c4 completed April 21, 2026, 12:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08ef91918c81908e99ab3a8ed9a1e5 completed May 16, 2026, 10:28 p.m.
NEDg Description generation batch_6a08f306e51481909691e3735ce10b60 completed May 16, 2026, 10:43 p.m.
NED2 Entity disambiguation (via description) batch_6a08f37adb908190a40a7bb1728f3dbf completed May 16, 2026, 10:45 p.m.
Created at: April 16, 2026, 12:37 p.m.