Triple
T4237006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hungnam evacuation |
E94717
|
entity |
| Predicate | numberOfEvacuatedCivilians |
P8973
|
FINISHED |
| Object | approximately 98000 |
—
|
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: approximately 98000 | Statement: [Hungnam evacuation, numberOfEvacuatedCivilians, approximately 98000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfEvacuatedCivilians Context triple: [Hungnam evacuation, numberOfEvacuatedCivilians, approximately 98000]
-
A.
numberOfEvacuated
chosen
Indicates the total count of individuals who have been evacuated from a location or situation.
-
B.
evacuatedBy
Indicates that an entity is removed or cleared from a place or situation through the action or assistance of another agent or process.
-
C.
evacuatedCity
Indicates that people or populations were removed from or left a city, typically due to danger or emergency conditions.
-
D.
notableEvacuation
Indicates a significant, widely recognized instance of people being moved or fleeing from a place for safety, typically due to danger or emergency conditions.
-
E.
evacuationMethod
Indicates the means or procedure by which people or objects are removed from a place of danger or risk.
- 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_69b34537cc6481909cd0a96acbb33ef7 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e7422a88190955f5f4347fa80d2 |
completed | March 12, 2026, 11:38 p.m. |
| PD | Predicate disambiguation | batch_69b347f3bd188190b0cd613e8a5c1683 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:05 p.m.