Triple
T349536
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hiryū |
E7410
|
entity |
| Predicate | survivorsRescuedBy |
P7320
|
FINISHED |
| Object | Japanese destroyers |
—
|
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: Japanese destroyers | Statement: [Hiryū, survivorsRescuedBy, Japanese destroyers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: survivorsRescuedBy Context triple: [Hiryū, survivorsRescuedBy, Japanese destroyers]
-
A.
rescuedBy
chosen
Indicates that one entity has been saved or brought out of danger by another entity.
-
B.
estimatedNumberOfPeopleSaved
Indicates the approximate count of individuals whose lives were preserved or harm was averted as a result of a particular action, intervention, or entity.
-
C.
estimatedNumberOfSurvivorsAtLiberation
Indicates the approximate count of individuals who were still alive at the time a camp or similar site was liberated.
-
D.
numberOfEvacuated
Indicates the total count of individuals who have been evacuated from a location or situation.
-
E.
sunkBy
Indicates that one entity (typically a vessel or structure) was caused to sink or be destroyed in water 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_69a2e7e696948190bebc966535995e45 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eb1dc5f88190b54d084c6def7fc5 |
completed | Feb. 28, 2026, 1:18 p.m. |
| PD | Predicate disambiguation | batch_69a2e955d1f88190bd687c46fa7c5469 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.