Triple
T24004089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Bridge |
E594323
|
entity |
| Predicate | wasSparedBy |
P21179
|
FINISHED |
| Object | retreating German forces in 1944 |
—
|
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: retreating German forces in 1944 | Statement: [Old Bridge, wasSparedBy, retreating German forces in 1944]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasSparedBy Context triple: [Old Bridge, wasSparedBy, retreating German forces in 1944]
-
A.
helpedEscape
Indicates that one entity assisted another in getting away from confinement, danger, or pursuit.
-
B.
laterSparedBy
Indicates that an entity was initially at risk but was subsequently spared or saved by another entity at a later time.
-
C.
sparedPerson
chosen
Indicates that one entity chose not to harm, punish, or otherwise negatively affect another entity when it had the power or opportunity to do so.
-
D.
isSurvivorOf
Indicates that one entity has lived through, endured, or remained alive after a particular event, condition, or harmful circumstance involving another entity.
-
E.
rescuedDuring
Indicates that one entity was rescued in the course of, or as part of, a specified event or time period.
- 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_69e288b9ecf08190b8c94a278f5674fe |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d4681fd88190949c5c91d4f94910 |
completed | April 29, 2026, 9:50 a.m. |
| PD | Predicate disambiguation | batch_69f17639d23c8190bed93434e2f9230a |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 9:40 p.m.