Triple

T22632332
Position Surface form Disambiguated ID Type / Status
Subject State of Song E558584 entity
Predicate borderedBy P224 FINISHED
Object State of Lu 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: State of Lu | Statement: [State of Song, borderedBy, State of Lu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: State of Lu
Context triple: [State of Song, borderedBy, State of Lu]
  • A. State of Lu chosen
    The State of Lu was an influential ancient Chinese feudal state during the Zhou dynasty, best known as the home state of Confucius and a center of early Confucian thought.
  • B. Soso state
    Soso state was a medieval West African kingdom that emerged from the decline of the Ghana Empire and later became part of the Mali Empire.
  • C. Tharad State
    Tharad State was a former princely state in British India that fell under the jurisdiction of the Palanpur Agency in what is now western India.
  • D. Tharoch State
    Tharoch State was a small princely hill state in the Simla Hills region of colonial India, ruled by local chiefs under British suzerainty.
  • E. Gondal State
    Gondal State was a princely state in western India, located in present-day Gujarat, known for its progressive reforms and modern infrastructure under its royal rulers.
  • 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_69e245467d9881908d6985bd0db7a1f1 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1700ab4308190a16b0a1b2a0210fd completed April 29, 2026, 2:42 a.m.
Created at: April 17, 2026, 3:02 p.m.