Triple

T28244167
Position Surface form Disambiguated ID Type / Status
Subject Battle of Guandu E712113 entity
Predicate laterHistorian P17033 FINISHED
Object Pei Songzhi 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: Pei Songzhi | Statement: [Battle of Guandu, laterHistorian, Pei Songzhi]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: laterHistorian
Context triple: [Battle of Guandu, laterHistorian, Pei Songzhi]
  • A. historian chosen
    Indicates that an entity studies, interprets, or writes about past events or historical subjects in relation to another entity.
  • B. historianAuthor
    Indicates that one entity is the historian who authored or wrote the work represented by the other entity.
  • C. historianDescribing
    Indicates that a historian is providing an account, explanation, or interpretation of a subject, event, or entity.
  • D. historicFor
    Indicates that something holds historical significance or importance specifically in relation to another entity.
  • E. historicalHeir
    Indicates that one entity is recognized as the successor or inheritor of another in a historical or dynastic context.
  • F. None of above.

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_69efb51fb98881909692421959ec0170 completed April 27, 2026, 7:12 p.m.
NER Named-entity recognition batch_69fd64bc86848190a49f451a8fc5cf1e completed May 8, 2026, 4:21 a.m.
PD Predicate disambiguation batch_69fd5ff4a648819090756d90fd195d9a completed May 8, 2026, 4 a.m.
Created at: April 27, 2026, 11 p.m.