Triple

T14614137
Position Surface form Disambiguated ID Type / Status
Subject Liang E343037 entity
Predicate hasVariant P455 FINISHED
Object Leung E982037 NE FINISHED

How this triple was built (2 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: Leung | Statement: [Liang, hasVariant, Leung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leung
Context triple: [Liang, hasVariant, Leung]
  • A. Leung chosen
    Leung is a common Chinese surname, particularly prevalent among Cantonese speakers and notable in Hong Kong and southern China.
  • B. Lawrence Leung
    Lawrence Leung is an Australian comedian, writer, and filmmaker known for his offbeat television series and stand-up shows that blend personal storytelling with nerdy pop-culture obsessions.
  • C. Shun-Tak Leung
    Shun-Tak Leung is a computer scientist known for co-authoring the influential Google File System paper on distributed storage infrastructure at Google.
  • D. Wing Lei
    Wing Lei is an upscale Chinese fine-dining restaurant at Wynn Las Vegas, renowned for its elegant décor and refined Cantonese cuisine.
  • E. Jimmy Lei Ba
    Jimmy Lei Ba is a machine learning researcher known for influential contributions to deep learning optimization and normalization techniques, including the development of Layer Normalization.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d822dec68081908c2553145c4051dc completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb45264988190a1df13e8b54a85bd completed April 14, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fda92110e88190af47b713dd24520b completed May 8, 2026, 9:13 a.m.
Created at: April 10, 2026, 1:25 a.m.