Triple
T8563468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Ivanovich |
E202743
|
entity |
| Predicate | firstScene |
P77498
|
FINISHED |
| Object | viewing of Ivan Ilyich’s corpse |
—
|
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: viewing of Ivan Ilyich’s corpse | Statement: [Peter Ivanovich, firstScene, viewing of Ivan Ilyich’s corpse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstScene Context triple: [Peter Ivanovich, firstScene, viewing of Ivan Ilyich’s corpse]
-
A.
firstAppearanceScene
chosen
Indicates the scene in which an entity is shown or referenced for the first time within a work or sequence.
-
B.
firstMission
Indicates that an entity is undertaking or associated with its initial mission or assignment in a given context.
-
C.
initialStage
Indicates that one entity represents the first or starting phase in a sequence, process, or development of another entity.
-
D.
firstStageDescription
Indicates that the value provides a textual explanation or summary of the initial or earliest stage in a multi-stage process or sequence.
-
E.
firstLocation
Indicates the initial or primary place where an entity is situated, originates, or where an event or relationship begins.
- 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_69ca8326e6c881908ff720d6abaebdc5 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe9cfc4a48190ae4530d3614d115f |
completed | March 31, 2026, 3:35 p.m. |
| PD | Predicate disambiguation | batch_69cbd11856048190a1ce4b83a38f6965 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:20 p.m.