Triple

T22632337
Position Surface form Disambiguated ID Type / Status
Subject State of Song E558584 entity
Predicate notableRuler P22 FINISHED
Object Duke Xiang of Song NE NERFINISHED

How this triple was built (3 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: Duke Xiang of Song | Statement: [State of Song, notableRuler, Duke Xiang of Song]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duke Xiang of Song
Context triple: [State of Song, notableRuler, Duke Xiang of Song]
  • A. Duke Wen of Chen
    Duke Wen of Chen was an early Zhou Dynasty ruler of the ancient Chinese State of Chen, remembered as one of its most prominent and formative dukes.
  • B. Duke Weizi of Song
    Duke Weizi of Song was an early Zhou dynasty noble, traditionally regarded as a younger brother of the last Shang king who was enfeoffed by the Zhou to establish the State of Song.
  • C. Duke Hu of Chen
    Duke Hu of Chen was an early Zhou dynasty noble who established the State of Chen as a hereditary feudal domain in ancient China.
  • D. Duke Xuan of Chen
    Duke Xuan of Chen was an early Zhou dynasty ruler of the ancient Chinese State of Chen, remembered primarily through traditional historical records of its line of dukes.
  • E. Duke Huan of Song
    Duke Huan of Song was an early Spring and Autumn period ruler of the ancient Chinese State of Song, remembered as one of its most prominent and historically significant dukes.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Duke Xiang of Song
Target entity description: Duke Xiang of Song was a Spring and Autumn period ruler of the ancient Chinese State of Song, remembered primarily for his rigid adherence to ritual propriety even in warfare, which led to his famous defeat at the Battle of Hongshui.
  • A. Duke Wen of Chen
    Duke Wen of Chen was an early Zhou Dynasty ruler of the ancient Chinese State of Chen, remembered as one of its most prominent and formative dukes.
  • B. Duke Weizi of Song
    Duke Weizi of Song was an early Zhou dynasty noble, traditionally regarded as a younger brother of the last Shang king who was enfeoffed by the Zhou to establish the State of Song.
  • C. Duke Hu of Chen
    Duke Hu of Chen was an early Zhou dynasty noble who established the State of Chen as a hereditary feudal domain in ancient China.
  • D. Duke Xuan of Chen
    Duke Xuan of Chen was an early Zhou dynasty ruler of the ancient Chinese State of Chen, remembered primarily through traditional historical records of its line of dukes.
  • E. Duke Huan of Song
    Duke Huan of Song was an early Spring and Autumn period ruler of the ancient Chinese State of Song, remembered as one of its most prominent and historically significant dukes.
  • F. None of above. chosen

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.