Triple

T17497862
Position Surface form Disambiguated ID Type / Status
Subject Ah Kee E426111 entity
Predicate connectedTo P37 FINISHED
Object Ling Moy NE NERFINISHED

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: Ling Moy | Statement: [Ah Kee, connectedTo, Ling Moy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ling Moy
Context triple: [Ah Kee, connectedTo, Ling Moy]
  • A. Ling Moy chosen
    Ling Moy is a central character in the 1931 crime film "Daughter of the Dragon," portrayed as a mysterious and pivotal figure within its early Hollywood depiction of Asian intrigue and villainy.
  • B. Lam Chau
    Lam Chau was a small island in Hong Kong that was largely reclaimed and merged into the site now occupied by Hong Kong International Airport at Chek Lap Kok.
  • C. Tonkin Liu
    Tonkin Liu is a British architecture and design practice known for its innovative, sculptural public artworks and environmentally responsive structures.
  • D. Tzu Chiang
    Tzu Chiang is the nickname of the AIDC AT-3, a Taiwanese advanced jet trainer and light attack aircraft.
  • E. Shong Lue Yang
    Shong Lue Yang was a Hmong spiritual leader and self-taught scholar best known for inventing the Pahawh Hmong writing system in the mid-20th century.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889dccf7481909264a1844a2e9100 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4520f6790819092c36e0e4ecc4cd3 completed April 19, 2026, 3:54 a.m.
Created at: April 10, 2026, 5:48 a.m.