Triple

T32493527
Position Surface form Disambiguated ID Type / Status
Subject Bonnie Parker and Clyde Barrow E830453 entity
Predicate ambushLeader P133110 FINISHED
Object Frank Hamer 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: Frank Hamer | Statement: [Bonnie Parker and Clyde Barrow, ambushLeader, Frank Hamer]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: ambushLeader
Context triple: [Bonnie Parker and Clyde Barrow, ambushLeader, Frank Hamer]
  • A. escapeLeader
    Indicates that one entity leads or initiates an escape in which another entity participates or follows.
  • B. escortCommander
    Indicates that one entity serves as the commanding officer responsible for leading or overseeing an escort force or mission involving another entity.
  • C. leader2 chosen
    Indicates that one entity serves as a leader, chief, or primary authority figure in relation to another entity.
  • D. assaultLedBy
    Indicates that an assault was directed or coordinated by a particular person or group.
  • E. victimLeader
    Indicates that one entity is the primary target or sufferer (the victim) in a situation where another entity holds a leading or directing role in causing or overseeing that victimization.
  • 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_69f34920aa4081908d8fb0277414b911 completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f6c4087e048190884d3902fdc81aa5 completed May 3, 2026, 3:42 a.m.
PD Predicate disambiguation batch_69f6bd25bed08190befcabd3a41ffadf completed May 3, 2026, 3:12 a.m.
Created at: May 1, 2026, 12:59 a.m.