Triple

T10083876
Position Surface form Disambiguated ID Type / Status
Subject Roger Perron E213969 entity
Predicate realPersonBehind P54368 FINISHED
Object character Roger Perron in The Conjuring 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: character Roger Perron in The Conjuring | Statement: [Roger Perron, realPersonBehind, character Roger Perron in The Conjuring]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: realPersonBehind
Context triple: [Roger Perron, realPersonBehind, character Roger Perron in The Conjuring]
  • A. basedOnRealPersonFor chosen
    Indicates that one entity is created, modeled, or inspired using a specific real person as its basis.
  • B. realName
    Indicates that one entity is the actual, full, or birth name of another entity, which may be known by an alias, nickname, or alternate identity.
  • C. frontPerson
    Indicates that one entity serves as the primary representative, leader, or public face positioned at the forefront in relation to another entity.
  • D. hasFrontPerson
    Indicates that an entity is represented, led, or fronted publicly by a specific person.
  • E. realityStatus
    Indicates the relationship between an entity and its state of existence or authenticity within a given context or world (e.g., real, fictional, hypothetical, simulated).
  • 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_69ca839bf730819086900c323c9b8c95 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd04352d081908f676444cd2d2578 completed April 2, 2026, 2:11 a.m.
PD Predicate disambiguation batch_69cd4b97870481908f7a89df10d58a9e completed April 1, 2026, 4:45 p.m.
Created at: March 30, 2026, 9 p.m.