Triple

T3586571
Position Surface form Disambiguated ID Type / Status
Subject Rachel Marron E75923 entity
Predicate hasBodyguard P957 FINISHED
Object Frank Farmer E55812 NE FINISHED

How this triple was built (3 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: Frank Farmer | Statement: [Rachel Marron, hasBodyguard, Frank Farmer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Farmer
Context triple: [Rachel Marron, hasBodyguard, Frank Farmer]
  • A. Frank Farmer chosen
    Frank Farmer is the stoic former Secret Service agent turned professional bodyguard who is hired to protect a famous singer in the film "The Bodyguard."
  • B. Brian Farmer
    Brian Farmer is a notable individual recognized for achievements significant enough to be distinguished among others sharing the surname Farmer.
  • C. Ed Farmer
    Ed Farmer was an American Major League Baseball pitcher and longtime Chicago White Sox radio broadcaster, best known for his tenure with and contributions to the White Sox organization.
  • D. Mark Farmer
    Mark Farmer is a British actor best known for his roles in the television series "Grange Hill," "Minder," and "Johnny Jarvis."
  • E. Todd Farmer
    Todd Farmer is an American screenwriter best known for his work on horror films such as "My Bloody Valentine 3D" and "Jason X."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasBodyguard
Context triple: [Rachel Marron, hasBodyguard, Frank Farmer]
  • A. hasSecurityTeam
    Indicates that an entity is supported or protected by a designated security team responsible for its safety or security operations.
  • B. guardian
    Indicates a protective or custodial relationship in which one entity is responsible for the care, safety, or oversight of another.
  • C. hasFlanker
    Indicates that an entity is positioned or assigned as a flanking support or protection alongside another entity.
  • D. hasWarden
    Indicates that one entity serves as the warden or supervisory authority responsible for another entity.
  • E. protectedBy chosen
    Indicates that one entity provides protection, defense, or safeguarding for another entity.
  • F. None of above.

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_69ad85d6dc3c8190b491b79b83e25461 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc137eb708190809cd52b6deb227c completed March 8, 2026, 6:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69b43303f1088190be5e4460f579efb8 completed March 13, 2026, 3:53 p.m.
PD Predicate disambiguation batch_69adb839b4e08190b1c0d611cccb11ae completed March 8, 2026, 5:56 p.m.
Created at: March 8, 2026, 3:22 p.m.