Triple

T35118805
Position Surface form Disambiguated ID Type / Status
Subject Tysha E1014112 entity
Predicate abusePerpetrator P172577 FINISHED
Object Tywin Lannister 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: Tywin Lannister | Statement: [Tysha, abusePerpetrator, Tywin Lannister]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: abusePerpetrator
Context triple: [Tysha, abusePerpetrator, Tywin Lannister]
  • A. perpetratorType
    Indicates the classification or category of the entity that carried out or is responsible for a harmful, illegal, or otherwise wrongful act.
  • B. perpetratorDescription
    Indicates that the subject provides a textual description or characterization of the perpetrator involved in an act or incident.
  • C. abuse
    Indicates that one entity mistreats, harms, or exploits another entity, often in a repeated or severe manner.
  • D. perpetratorInCase chosen
    Indicates that an entity is the person or group responsible for committing the offense or wrongdoing in a particular legal or investigative case.
  • E. perpetratorStatus
    Indicates the role or condition of an individual in relation to committing or being responsible for a specific harmful or criminal act.
  • 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_69f76dd8b6948190aaa32b081816bd94 completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69f78ce78b508190955848e133398dc8 completed May 3, 2026, 5:59 p.m.
PD Predicate disambiguation batch_69f78b8f4cc08190b49fccd798cb25d7 completed May 3, 2026, 5:53 p.m.
Created at: May 3, 2026, 4:01 p.m.