Triple
T33593687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karla’s Moscow Centre |
E860499
|
entity |
| Predicate | hasKeyAdversary |
P188123
|
FINISHED |
| Object | George Smiley |
—
|
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: George Smiley | Statement: [Karla’s Moscow Centre, hasKeyAdversary, George Smiley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeyAdversary Context triple: [Karla’s Moscow Centre, hasKeyAdversary, George Smiley]
-
A.
hasKeyPass
Indicates that an entity possesses or is granted a key-based pass that allows access or authorization to something.
-
B.
hasKeyAccord
Indicates that one entity possesses or defines the primary key or governing agreement that authorizes or controls another entity.
-
C.
hasKeyDecision
Indicates that an entity holds primary responsibility or authority for making a significant decision in a given context.
-
D.
hasKeyTheorem
Indicates that one entity contains, relies on, or is characterized by a central or foundational theorem associated with the other entity.
-
E.
hasKeyAct
Indicates that one entity possesses or is associated with a primary or central action related to another entity.
- F. None of above. chosen
Provenance (4 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_69f3497e70e48190951c94d072879bec |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fba2877b248190a974eb092243c0c4 |
completed | May 6, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69fb8d06a1b48190a937aa410d159dfa |
completed | May 6, 2026, 6:48 p.m. |
| PDg | Predicate description generation | batch_69fba28684208190921694f23e350c3b |
completed | May 6, 2026, 8:20 p.m. |
Created at: May 1, 2026, 1:41 a.m.