Triple

T7968619
Position Surface form Disambiguated ID Type / Status
Subject Law Kar-ying E185267 entity
Predicate collaboratedWith P435 FINISHED
Object Liza Wang E704789 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: Liza Wang | Statement: [Law Kar-ying, collaboratedWith, Liza Wang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liza Wang
Context triple: [Law Kar-ying, collaboratedWith, Liza Wang]
  • A. Liza Wang chosen
    Liza Wang is a renowned Hong Kong actress and Cantonese opera star, celebrated as one of the most influential figures in the local entertainment industry.
  • B. Lily Mei
    Lily Mei is an American politician who has served as the mayor of Fremont, California, and is noted as one of the first Asian American women to lead a large U.S. city.
  • C. Erica Li
    Erica Li is a Hong Kong screenwriter known for her work on contemporary Chinese-language films and television dramas.
  • D. Billie Tsien
    Billie Tsien is an American architect renowned for her thoughtful, materially rich institutional and cultural buildings, often designed in collaboration with her partner Tod Williams.
  • E. Ellen Lee Zhou
    Ellen Lee Zhou is a conservative social worker and community activist known for her long-shot campaigns for mayor of San Francisco, where she has promoted tough-on-crime and anti-establishment policies.
  • 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_69ca8297699481909b75a405f01e03af completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3bd06ee081908c5080003fb7b8f7 completed March 31, 2026, 3:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc566afad88190b53f228d836619de completed March 31, 2026, 11:19 p.m.
Created at: March 30, 2026, 5:13 p.m.