Triple
T8513412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shawshank State Penitentiary |
E201511
|
entity |
| Predicate | notableEventInFiction |
P39504
|
FINISHED |
| Object | Andy Dufresne’s escape |
—
|
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: Andy Dufresne’s escape | Statement: [Shawshank State Penitentiary, notableEventInFiction, Andy Dufresne’s escape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableEventInFiction Context triple: [Shawshank State Penitentiary, notableEventInFiction, Andy Dufresne’s escape]
-
A.
notableWorkInPlot
Indicates that a work is prominently featured or plays a significant role within the plot of another work.
-
B.
notableStoryArc
chosen
Indicates that there exists a significant or prominent narrative storyline or plot development involving the subject.
-
C.
notableEventInLife
Indicates that a particular event holds significant importance or impact within an entity’s life or personal history.
-
D.
notableEventResponse
Indicates a response, reaction, or consequence that occurs as a result of a notable event.
-
E.
notableCoverEvent
Indicates that an entity has been the subject of a particularly significant or noteworthy cover version, performance, or reinterpretation by another entity.
- 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_69ca8320e5748190ac2c585a0bba8193 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe60cdfcc819081a9be1229378ba0 |
completed | March 31, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69cbd10cfd208190a519049fad32c508 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:15 p.m.