Triple

T19345921
Position Surface form Disambiguated ID Type / Status
Subject Squire and Partners E483876 entity
Predicate hasKeyPerson P256 FINISHED
Object Maria Cheung
Maria Cheung is a key architect and design leader at the London-based architecture practice Squire and Partners.
E1370920 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: Maria Cheung | Statement: [Squire and Partners, hasKeyPerson, Maria Cheung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maria Cheung
Context triple: [Squire and Partners, hasKeyPerson, Maria Cheung]
  • A. Selina Tsang
    Selina Tsang is the wife of former Hong Kong Chief Executive Donald Tsang and a public figure known primarily for her role as his spouse in Hong Kong’s political and social circles.
  • B. Regina Leung
    Regina Leung is a Hong Kong public figure best known as the wife of former Chief Executive Leung Chun-ying and for her involvement in charitable and community activities.
  • C. Miriam Yeung
    Miriam Yeung is a prominent Hong Kong Cantopop singer and actress known for her hit ballads and successful film roles.
  • D. Teresa Cheng
    Teresa Cheng is a film producer known for her work on major animated features, including entries in the Shrek franchise.
  • E. Selina Lo
    Selina Lo is an actress and martial artist known for her roles in action and fantasy films.
  • 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: Maria Cheung
Triple: [Squire and Partners, hasKeyPerson, Maria Cheung]
Generated description
Maria Cheung is a key architect and design leader at the London-based architecture practice Squire and Partners.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maria Cheung
Target entity description: Maria Cheung is a key architect and design leader at the London-based architecture practice Squire and Partners.
  • A. Selina Tsang
    Selina Tsang is the wife of former Hong Kong Chief Executive Donald Tsang and a public figure known primarily for her role as his spouse in Hong Kong’s political and social circles.
  • B. Regina Leung
    Regina Leung is a Hong Kong public figure best known as the wife of former Chief Executive Leung Chun-ying and for her involvement in charitable and community activities.
  • C. Miriam Yeung
    Miriam Yeung is a prominent Hong Kong Cantopop singer and actress known for her hit ballads and successful film roles.
  • D. Teresa Cheng
    Teresa Cheng is a film producer known for her work on major animated features, including entries in the Shrek franchise.
  • E. Selina Lo
    Selina Lo is an actress and martial artist known for her roles in action and fantasy films.
  • 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_69d8e8d244f8819080eb1f3491300db2 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e6185a56b4819089336564959b84df completed April 20, 2026, 12:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a071bed1c608190a71094aa2645199d completed May 15, 2026, 1:13 p.m.
NEDg Description generation batch_6a071cc1c76c8190b99ef2b319f6ab39 completed May 15, 2026, 1:16 p.m.
NED2 Entity disambiguation (via description) batch_6a071d787dd881908d86c5fe52ca2561 completed May 15, 2026, 1:19 p.m.
Created at: April 10, 2026, 1:34 p.m.