Triple

T18572299
Position Surface form Disambiguated ID Type / Status
Subject Raffles Institution E453901 entity
Predicate hasAlumnus P51 FINISHED
Object Adrian Tan
Adrian Tan was a prominent Singaporean lawyer and author best known for his satirical novels and leadership in the legal community.
E1333537 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 Tan | Statement: [Raffles Institution, hasAlumnus, Adrian Tan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adrian Tan
Context triple: [Raffles Institution, hasAlumnus, Adrian Tan]
  • A. Adam Tan
    Adam Tan is a Chinese business executive best known as a top leader of the HNA Group conglomerate.
  • B. Gabriel Goh
    Gabriel Goh is a machine learning researcher known for his work at OpenAI, including co-developing the CLIP model for connecting images and text.
  • C. Vincent Tan
    Vincent Tan is a Malaysian billionaire businessman and investor best known for owning multiple football clubs, including Cardiff City FC, and for founding the Berjaya Corporation conglomerate.
  • D. Adrian Wong
    Adrian Wong is a Hong Kong actor and television personality known for his work in local dramas and variety shows.
  • E. Adrian Lau
    Adrian Lau is a hip-hop artist and rapper known for his collaborations within the underground rap scene.
  • 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 Tan
Triple: [Raffles Institution, hasAlumnus, Adrian Tan]
Generated description
Adrian Tan was a prominent Singaporean lawyer and author best known for his satirical novels and leadership in the legal community.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Adrian Tan
Target entity description: Adrian Tan was a prominent Singaporean lawyer and author best known for his satirical novels and leadership in the legal community.
  • A. Adam Tan
    Adam Tan is a Chinese business executive best known as a top leader of the HNA Group conglomerate.
  • B. Gabriel Goh
    Gabriel Goh is a machine learning researcher known for his work at OpenAI, including co-developing the CLIP model for connecting images and text.
  • C. Vincent Tan
    Vincent Tan is a Malaysian billionaire businessman and investor best known for owning multiple football clubs, including Cardiff City FC, and for founding the Berjaya Corporation conglomerate.
  • D. Adrian Wong
    Adrian Wong is a Hong Kong actor and television personality known for his work in local dramas and variety shows.
  • E. Adrian Lau
    Adrian Lau is a hip-hop artist and rapper known for his collaborations within the underground rap scene.
  • 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_69d8d38974308190a9174430ef256b73 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53b032488819098de683bb5c42c4b completed April 19, 2026, 8:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0503761830819088f36a34e377ff49 completed May 13, 2026, 11:04 p.m.
NEDg Description generation batch_6a050537da5481908da9209410986124 completed May 13, 2026, 11:11 p.m.
NED2 Entity disambiguation (via description) batch_6a0505e91794819086506a77ef287645 completed May 13, 2026, 11:14 p.m.
Created at: April 10, 2026, 11:43 a.m.