Triple
T31262958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Cairncross |
E797171
|
entity |
| Predicate | confessed to |
P4081
|
FINISHED |
| Object | spying for the Soviet Union |
—
|
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: spying for the Soviet Union | Statement: [John Cairncross, confessed to, spying for the Soviet Union]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: confessed to Context triple: [John Cairncross, confessed to, spying for the Soviet Union]
-
A.
confessedTo
chosen
Indicates that one entity admitted guilt or revealed the truth about an action, wrongdoing, or secret to another entity.
-
B.
confessedAs
Indicates that one entity has admitted or acknowledged being or doing something, typically revealing guilt, identity, or involvement in relation to another entity.
-
C.
confessedAction
Indicates that an entity has admitted to performing a particular action, typically acknowledging responsibility or guilt.
-
D.
confessedFor
Indicates that one entity admitted guilt or responsibility on behalf of another entity.
-
E.
confesses
Indicates that one entity openly admits or acknowledges something, typically a wrongdoing, secret, or previously concealed fact, to 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_69f224dd5fdc81908a4cd24917b67668 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7764ab1fc81909f9348db87bd7692 |
completed | May 3, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f76905d9c88190b1ee810bc9ab644f |
completed | May 3, 2026, 3:25 p.m. |
Created at: April 29, 2026, 9:12 p.m.