Triple
T33307683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sudden Departure |
E852779
|
entity |
| Predicate | populationPercentageAffected |
P158710
|
FINISHED |
| Object | 2% |
—
|
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: 2% | Statement: [Sudden Departure, populationPercentageAffected, 2%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: populationPercentageAffected Context triple: [Sudden Departure, populationPercentageAffected, 2%]
-
A.
estimatedAffectedPeople
Indicates the estimated number of people expected to be impacted by a particular event, condition, or action.
-
B.
populationLoss
Indicates a decrease in the number of individuals within a defined population over a given period or due to specific causes.
-
C.
populationShareApproximate
chosen
Indicates that one entity’s share of a total population is approximately equal to a specified proportion or percentage, allowing for some margin of error.
-
D.
numberOfDistrictsHeavilyDamaged
Indicates the count of districts that have sustained severe or heavy damage in a given context or event.
-
E.
populationState
Indicates the condition or status of a population at a given point in time, such as its size, distribution, or demographic characteristics.
- 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_69f349679fd8819093b9b40e989440e3 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 1, 2026, 1:33 a.m.