Triple
T25020024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adolf Verloc |
E626545
|
entity |
| Predicate | doubleAgentFor |
P157546
|
FINISHED |
| Object | foreign embassy |
—
|
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: foreign embassy | Statement: [Adolf Verloc, doubleAgentFor, foreign embassy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doubleAgentFor Context triple: [Adolf Verloc, doubleAgentFor, foreign embassy]
-
A.
doubleAgentFor
chosen
Indicates that an entity secretly works as an agent for two opposing sides, typically betraying at least one of them.
-
B.
Double-AAffiliate
Indicates a relationship where an entity is simultaneously affiliated with two separate organizations, groups, or programs in a recognized, parallel capacity.
-
C.
dualIntent
Indicates that an action or statement is performed with two simultaneous, distinct purposes or motivations.
-
D.
secondParty
Indicates that an entity participates in a relationship or transaction as the second party relative to a primary (first) party.
-
E.
hasOpposingAgent
Indicates that an entity is opposed or counteracted by another agent in a given context or interaction.
- 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_69e2ff28ee3881909c626af002457a4a |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f464b4c9b0819085daa00c7c3b8b76 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f45cfb53f4819099bba48c5057e787 |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 18, 2026, 6:06 a.m.