Triple

T1163649
Position Surface form Disambiguated ID Type / Status
Subject The Prime Minister E24549 entity
Predicate hasFictionalRole P25662 FINISHED
Object depicts a British Prime Minister in office LITERAL FINISHED

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: depicts a British Prime Minister in office | Statement: [The Prime Minister, hasFictionalRole, depicts a British Prime Minister in office]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasFictionalRole
Context triple: [The Prime Minister, hasFictionalRole, depicts a British Prime Minister in office]
  • A. playedRoleIn
    Indicates that an entity performed or assumed a specific role or character within a particular event, production, or context.
  • B. hasFamousNamesakeRole
    Indicates that an entity has a role or position that shares its name with a well-known or historically notable person.
  • C. actingRoleType
    Indicates the specific type or category of role an entity performs when acting in a particular capacity or function.
  • D. creativeRole
    Indicates that an entity holds a specific creative function or responsibility in relation to another entity, such as a work or project.
  • E. playedBy
    Indicates that a role, character, or performance is portrayed or executed by a specific person or agent.
  • 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_69a494060e148190abb42f971242c197 completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bcc9dc5081908e225a485186ab12 completed March 1, 2026, 10:25 p.m.
PD Predicate disambiguation batch_69a4bb525b648190adcb7a29256d3c41 completed March 1, 2026, 10:18 p.m.
PDg Predicate description generation batch_69a4bc49693c8190978ec63a5171d342 completed March 1, 2026, 10:23 p.m.
Created at: March 1, 2026, 7:45 p.m.