Triple

T14366088
Position Surface form Disambiguated ID Type / Status
Subject Mukden Palace E356237 entity
Predicate locatedIn P40 FINISHED
Object Shenyang E20553 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: Shenyang | Statement: [Mukden Palace, locatedIn, Shenyang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shenyang
Context triple: [Mukden Palace, locatedIn, Shenyang]
  • A. Shenyang chosen
    Shenyang is a major industrial and historical city in northeastern China and the capital of Liaoning Province.
  • B. Dalian
    Dalian is a major port city in northeastern China known for its strategic location on the Liaodong Peninsula, maritime trade, and modern urban development.
  • C. Liaoyuan
    Liaoyuan is a prefecture-level city in northeastern China known for its coal mining history and location in the central part of Jilin Province.
  • D. Changchun
    Changchun is a major city in northeastern China that served as the capital of the Japanese puppet state of Manchukuo during the early 20th century.
  • E. Anshan
    Anshan was an ancient city and region in southwestern Iran that served as an early center of Elamite and later Achaemenid Persian power.
  • 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_69d8279163a081908aec45c0e3f1e02f completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8fad48748190a0f34ca4d02f9a3c completed April 14, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd550e677c8190837c3b9ccb64f0cd completed May 8, 2026, 3:14 a.m.
Created at: April 10, 2026, 1:15 a.m.