Triple
T9126782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cyclone Nargis |
E218984
|
entity |
| Predicate | missingPersonsEstimate |
P87238
|
FINISHED |
| Object | over 50000 people |
—
|
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: over 50000 people | Statement: [Cyclone Nargis, missingPersonsEstimate, over 50000 people]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: missingPersonsEstimate Context triple: [Cyclone Nargis, missingPersonsEstimate, over 50000 people]
-
A.
numberOfSuspectedVictims
Indicates the count of individuals believed or alleged to be victims in a particular incident, case, or context.
-
B.
populationEstimateLoss
Indicates a reduction or decrease in a previously estimated population size.
-
C.
estimatedPrisoners
Indicates a relationship where a value represents the estimated number of prisoners associated with a particular entity or context.
-
D.
numberOfNamesOnWallOfMissing
Indicates the count of individual names that appear on a designated wall listing missing persons.
-
E.
numberOfUnidentifiedRemains
Indicates the count of human remains that have not yet been identified in a given context or case.
- F. None of above. chosen
Provenance (4 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. |
| PDg | Predicate description generation | batch_69cc6a3c78388190a7436acc0e44ff55 |
completed | April 1, 2026, 12:43 a.m. |
Created at: March 30, 2026, 7:18 p.m.