Triple
T34011609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donald Maclean |
E872127
|
entity |
| Predicate | coDefector |
P12199
|
FINISHED |
| Object | Guy Burgess |
—
|
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: Guy Burgess | Statement: [Donald Maclean, coDefector, Guy Burgess]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coDefector Context triple: [Donald Maclean, coDefector, Guy Burgess]
-
A.
coDefendant
Indicates that two or more parties are jointly named and involved as defendants in the same legal case or proceeding.
-
B.
defectedTo
chosen
Indicates that an entity abandoned its original side, group, or allegiance and joined or gave support to another, typically opposing, side.
-
C.
otherAdversary
Indicates that one entity is an adversary of another, distinct from any primary or previously identified adversary.
-
D.
antagonistOf
Indicates a relationship where one entity actively opposes, conflicts with, or serves as an adversary to another.
-
E.
defender
Indicates a relationship where one entity protects, guards, or supports another entity against threats, attacks, or criticism.
- 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_69f349a08848819084b348d64c1879c3 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f70b966860819089cf92927f47c5f1 |
completed | May 3, 2026, 8:47 a.m. |
| PD | Predicate disambiguation | batch_69f70abe43e08190b2a30930d96247c1 |
completed | May 3, 2026, 8:43 a.m. |
Created at: May 1, 2026, 1:51 a.m.