Triple
T24176642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perce Blackborow |
E599299
|
entity |
| Predicate | rescueFrom |
P155594
|
FINISHED |
| Object | Elephant Island |
—
|
NE NERFINISHED |
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: Elephant Island | Statement: [Perce Blackborow, rescueFrom, Elephant Island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rescueFrom Context triple: [Perce Blackborow, rescueFrom, Elephant Island]
-
A.
rescueBy
Indicates that one entity is saved or freed from danger, harm, or a problematic situation by another entity.
-
B.
rescueDomain
Indicates that one entity saves or retrieves another entity from danger, harm, or a problematic situation within a particular domain or context.
-
C.
attemptedRescueBy
Indicates an action where one entity made an effort to save or free another entity from danger, harm, or a problematic situation.
-
D.
rescuedByProxy
Indicates that an entity is saved or freed from danger or harm through the actions or intervention of an intermediary acting on behalf of another.
-
E.
rescueDate
Indicates the date on which a rescue action or operation took place.
- F. None of above. chosen
Provenance (4 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_69e288cca05481908faeb1563711114a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27c9ddfcc819096697a844b300cce |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c42f942c8190b103ff29a60fef34 |
completed | April 29, 2026, 8:41 a.m. |
| PDg | Predicate description generation | batch_69f27a753ca8819095706970d368f762 |
completed | April 29, 2026, 9:39 p.m. |
Created at: April 17, 2026, 11:34 p.m.