Triple
T5096382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tacloban |
E114874
|
entity |
| Predicate | disasterTypeExperienced |
P15089
|
FINISHED |
| Object | storm surge |
—
|
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: storm surge | Statement: [Tacloban, disasterTypeExperienced, storm surge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disasterTypeExperienced Context triple: [Tacloban, disasterTypeExperienced, storm surge]
-
A.
hasDisaster
chosen
Indicates that an entity experiences, is affected by, or is associated with a disaster event.
-
B.
supportsDisasterType
Indicates that one entity is capable of handling, responding to, or being applicable to a specified type of disaster.
-
C.
facedMajorEarthquake
Indicates that an entity has experienced or been subjected to a significant or severe earthquake event.
-
D.
hasNaturalHazardRisk
Indicates that an entity is exposed or subject to potential damage or impact from one or more natural hazards (e.g., earthquakes, floods, storms).
-
E.
experiencedMajorTsunami
Indicates that the subject has undergone or been affected by a large-scale, significant tsunami event.
- 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_69bd443fc49c819089629c00e311310c |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75652a8081908386718f1fdb1de3 |
completed | March 20, 2026, 4:27 p.m. |
| PD | Predicate disambiguation | batch_69bd715e06808190931934dc9930f997 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:40 p.m.