Triple

T26369127
Position Surface form Disambiguated ID Type / Status
Subject Sun clan E660722 entity
Predicate producedWarlord P174665 FINISHED
Object Sun Jian 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: Sun Jian | Statement: [Sun clan, producedWarlord, Sun Jian]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: producedWarlord
Context triple: [Sun clan, producedWarlord, Sun Jian]
  • A. warlordCharacter
    Indicates that one entity plays the role or has the characteristics of a warlord in relation to another entity or within a given context.
  • B. wargBond
    Indicates a special bond or partnership between a warg and another entity, typically involving loyalty, cooperation, or shared purpose.
  • C. isWarHeroOf
    Indicates that one entity is recognized as a war hero in relation to, or on behalf of, another entity (such as a country, group, or cause).
  • D. laterWarProductionFeature
    Indicates that the subject possesses a characteristic or attribute specifically associated with a later phase of war-related production.
  • E. preeminentWarlordLineage
    Indicates that one entity descends from or belongs to a lineage recognized as the foremost or most dominant among warlords.
  • F. None of above. chosen

Provenance (4 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_69ee812a698881908d6a58265995fa39 completed April 26, 2026, 9:18 p.m.
NER Named-entity recognition batch_69f6c5b7e46081909975b05f7298cc0e completed May 3, 2026, 3:49 a.m.
PD Predicate disambiguation batch_69f6c3f23ae081909a52801266063a3c completed May 3, 2026, 3:41 a.m.
PDg Predicate description generation batch_69f6c49069e48190a3486b6254a6645b completed May 3, 2026, 3:44 a.m.
Created at: April 26, 2026, 10:57 p.m.