Triple
T7953488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frankie Yale |
E184671
|
entity |
| Predicate | suspectedKillers |
P21177
|
FINISHED |
| Object | gunmen linked to Al Capone (historical speculation) |
—
|
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: gunmen linked to Al Capone (historical speculation) | Statement: [Frankie Yale, suspectedKillers, gunmen linked to Al Capone (historical speculation)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: suspectedKillers Context triple: [Frankie Yale, suspectedKillers, gunmen linked to Al Capone (historical speculation)]
-
A.
hasSerialKiller
Indicates that one entity is a serial killer associated with, responsible for, or targeting another entity.
-
B.
suspectedPerpetrator
chosen
Indicates that an entity is believed or alleged to be the person responsible for committing a particular harmful or illegal act.
-
C.
murderedIn
Indicates that one entity unlawfully killed another entity at or within a specified location.
-
D.
allegedToHaveKilled
Indicates that one entity is claimed or accused, but not proven, to have killed another entity.
-
E.
reasonForMurder
Indicates the motive or underlying cause that led someone to commit a murder.
- 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_69ca8292cba881908a64427b938dac47 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3b5e51c88190abcc0534723e3660 |
completed | March 31, 2026, 3:11 a.m. |
| PD | Predicate disambiguation | batch_69cb0473d7dc8190a25d0cf460b9fcbe |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:10 p.m.