Triple
T9126779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cyclone Nargis |
E218984
|
entity |
| Predicate | damageEstimate |
P25888
|
FINISHED |
| Object | approximately 12.9 billion USD |
—
|
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 12.9 billion USD | Statement: [Cyclone Nargis, damageEstimate, approximately 12.9 billion USD]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: damageEstimate Context triple: [Cyclone Nargis, damageEstimate, approximately 12.9 billion USD]
-
A.
economicDamageApprox
chosen
Indicates that one entity has caused or is associated with an estimated or approximate amount of economic damage to another entity or system.
-
B.
economicDamage
Indicates that one entity causes or experiences financial loss, harm, or negative economic impact as a result of another entity or event.
-
C.
damageLeadsTo
Indicates that one instance of damage causally results in or contributes to another specified outcome or condition.
-
D.
economicDamageRank
Indicates the relative severity or position of an entity in terms of the economic damage it causes or experiences compared to others.
-
E.
damageTo
Indicates a relationship where one entity causes harm, loss, or deterioration to 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_69ca83debfc0819095800583e97ab10f |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8c93d3c8190b003b2b1af2003b2 |
completed | April 1, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69cc66003e3c819091e1e42c9cf7c781 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:18 p.m.