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.