Triple
T38010362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stephen Blackpool |
E948346
|
entity |
| Predicate | isInnocentOf |
P113649
|
FINISHED |
| Object | bank robbery |
—
|
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: bank robbery | Statement: [Stephen Blackpool, isInnocentOf, bank robbery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInnocentOf Context triple: [Stephen Blackpool, isInnocentOf, bank robbery]
-
A.
actuallyInnocentOf
chosen
Indicates that an entity is truly not responsible for or did not commit the action, offense, or wrongdoing in question, regardless of prior accusations or judgments.
-
B.
claimedInnocenceOf
Indicates that one entity asserts or maintains that another entity is not guilty of a particular accusation or wrongdoing.
-
C.
provesInnocenceBy
Indicates that one party establishes or demonstrates another party’s lack of guilt through evidence, argument, or legal process.
-
D.
acquittedOf
Indicates that an authority has formally cleared an entity of a specific charge, accusation, or wrongdoing.
-
E.
worksToProveInnocenceOf
Indicates that one entity actively engages in efforts or actions aimed at demonstrating or establishing the innocence of another entity.
- 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_69f76efb4b10819092c8c2ba28ac06a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.