Triple
T31094015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madeline's Rescue |
E792475
|
entity |
| Predicate | hasRescueScene |
P151421
|
FINISHED |
| Object | Madeline is saved from the Seine by a dog |
—
|
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: Madeline is saved from the Seine by a dog | Statement: [Madeline's Rescue, hasRescueScene, Madeline is saved from the Seine by a dog]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRescueScene Context triple: [Madeline's Rescue, hasRescueScene, Madeline is saved from the Seine by a dog]
-
A.
hasMiracleScene
Indicates that a scene involves a miraculous or supernatural event occurring.
-
B.
hasCrimeScene
Indicates that a particular location or setting is the site where a specific crime occurred or was discovered.
-
C.
rescueOperation
chosen
Indicates an action where one entity undertakes efforts to save or free another entity from danger, harm, or a threatening situation.
-
D.
hasRegionalScene
Indicates that something possesses or is associated with a specific regional scene, such as a localized cultural, artistic, or social milieu.
-
E.
hasRescueServices
Indicates that one entity provides or is equipped with rescue or emergency response services for another entity or area.
- 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_69f224cf157c81909e2d2bd88c9282c3 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a00d6aff0a08190a330dd0c7c1352f9 |
completed | May 10, 2026, 7:04 p.m. |
| PD | Predicate disambiguation | batch_6a00d60f2a508190aeaf5a9d8af9c39e |
completed | May 10, 2026, 7:01 p.m. |
Created at: April 29, 2026, 9:03 p.m.