Triple
T30421508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashley Graham |
E773912
|
entity |
| Predicate | rescuedEnding |
P55743
|
FINISHED |
| Object | escapes Spain with Leon S. Kennedy |
—
|
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: escapes Spain with Leon S. Kennedy | Statement: [Ashley Graham, rescuedEnding, escapes Spain with Leon S. Kennedy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rescuedEnding Context triple: [Ashley Graham, rescuedEnding, escapes Spain with Leon S. Kennedy]
-
A.
rescuedTo
Indicates that one entity has been saved or freed from danger, harm, or a problematic situation and brought to the safety or custody of another entity or location.
-
B.
rescuedDuring
Indicates that one entity was rescued in the course of, or as part of, a specified event or time period.
-
C.
rescuedInFormOf
Indicates that one entity is rescued, saved, or recovered specifically in the form, state, or manifestation represented by another entity.
-
D.
rescuedLocation
Indicates the place where a rescue action occurred or from which someone or something was rescued.
-
E.
alternateEnding
chosen
Indicates that one version of a work provides a different conclusion or final sequence of events compared to the original or primary ending.
- 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_69f22491ba248190b9a4776ca8e42d02 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68663d49c81908c44b8cb0f31d014 |
completed | May 2, 2026, 11:19 p.m. |
| PD | Predicate disambiguation | batch_69f67e40af9881908de3a4aa15f70a83 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:06 p.m.