Triple
T19619544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Cullen |
E470960
|
entity |
| Predicate | keyPlotFunction |
P88311
|
FINISHED |
| Object | exposes corporate and government corruption |
—
|
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: exposes corporate and government corruption | Statement: [Lee Cullen, keyPlotFunction, exposes corporate and government corruption]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyPlotFunction Context triple: [Lee Cullen, keyPlotFunction, exposes corporate and government corruption]
-
A.
primaryFunctionInPlot
chosen
Indicates the main narrative role or purpose that an entity serves within the plot of a story.
-
B.
keyFunction
Indicates that an entity serves as a primary or essential mechanism enabling a particular operation, role, or outcome for another entity.
-
C.
isKeyToPlotOf
Indicates that something plays a crucial, defining role in driving or enabling the main events or structure of a plot.
-
D.
coordinatesFunction
Indicates a relationship where one entity organizes, schedules, or manages the execution of a function or activity involving other entities.
-
E.
peakFunction
Indicates that a function reaches a maximum (peak) value at a specific point or over a given interval.
- 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640e4570c81909fc4f9b871346337 |
completed | April 20, 2026, 3:06 p.m. |
| PD | Predicate disambiguation | batch_69e514e5cb108190ae260e466c447314 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:43 p.m.