Triple
T17890800
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SMERSH (in the novel) |
E447309
|
entity |
| Predicate | commandStructureInFiction |
P129178
|
FINISHED |
| Object | under Soviet state security apparatus |
—
|
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: under Soviet state security apparatus | Statement: [SMERSH (in the novel), commandStructureInFiction, under Soviet state security apparatus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commandStructureInFiction Context triple: [SMERSH (in the novel), commandStructureInFiction, under Soviet state security apparatus]
-
A.
conductsInFiction
Indicates that an entity carries out or performs an action or role within a fictional context or narrative.
-
B.
languageWithinFiction
Indicates that a language is used or exists within the context of a fictional work or fictional universe.
-
C.
coDesignerInFiction
Indicates that two or more entities are credited as co-designers of a fictional work, setting, or in-universe creation.
-
D.
workInFiction
Indicates that one entity is a fictional work in which the other entity appears or is set.
-
E.
positionInFiction
Indicates that one entity holds a specific role, status, or placement within a fictional work or narrative.
- 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_69d8b9f59bd48190a6fc925a855b8bac |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49d7948888190b59ddc7061d13e84 |
completed | April 19, 2026, 9:16 a.m. |
| PD | Predicate disambiguation | batch_69e3d8e9b77c8190bbfb508f28dfacfa |
completed | April 18, 2026, 7:18 p.m. |
| PDg | Predicate description generation | batch_69e3db7704588190a34a422421152173 |
completed | April 18, 2026, 7:28 p.m. |
Created at: April 10, 2026, 10:18 a.m.