Triple

T20566530
Position Surface form Disambiguated ID Type / Status
Subject Zhongyong E504978 entity
Predicate includedIn P1393 FINISHED
Object Liji 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: Liji | Statement: [Zhongyong, includedIn, Liji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liji
Context triple: [Zhongyong, includedIn, Liji]
  • A. Liji chosen
    Liji is a foundational Confucian classic that systematically outlines traditional Chinese rites, social norms, and moral principles.
  • B. L.J.
    L.J. is a comic-relief survivor and ally of the protagonists in the film Resident Evil: Apocalypse, known for his streetwise attitude and humorous one-liners amid the zombie outbreak.
  • C. Liew
    Liew is a romanized variant of the Chinese surname commonly spelled as Liu.
  • D. Lija
    Lija is a small, picturesque village in central Malta known for its traditional architecture, quiet residential character, and annual fireworks displays.
  • E. Luli
    Luli is a dialect of the Paama language, spoken by a subset of Paama speakers in Vanuatu.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a7a33f7c8190966da03528dfe8aa completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.