Triple
T3052299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cyclone Tracy |
E60397
|
entity |
| Predicate | damagedBuildings |
P1583
|
FINISHED |
| Object | over 90 percent of Darwin’s buildings |
—
|
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 90 percent of Darwin’s buildings | Statement: [Cyclone Tracy, damagedBuildings, over 90 percent of Darwin’s buildings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: damagedBuildings Context triple: [Cyclone Tracy, damagedBuildings, over 90 percent of Darwin’s buildings]
-
A.
buildingsDestroyed
chosen
Indicates that one or more buildings have been damaged to the point of destruction as a result of some event or action.
-
B.
destroyedCity
Indicates that an entity has caused the complete or near-complete destruction of a city.
-
C.
demolishedOriginalStructures
Indicates that one entity has completely destroyed or removed the original structures associated with another entity.
-
D.
damagedIn
Indicates that an entity has suffered harm, impairment, or destruction as a result of a specified event, process, or condition.
-
E.
sufferedDestructionIn
Indicates that an entity experienced damage, ruin, or devastation during or as part of a specified event or period.
- 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_69ad8578137c81908259dcb27c7d6d7c |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ad9bf3c52c8190bbe8e5cb98c21715 |
completed | March 8, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69ad962195388190856013a2519c2b0f |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:01 p.m.