Triple
T6265022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hurricane Maria |
E140391
|
entity |
| Predicate | dateOfLandfall |
P69049
|
FINISHED |
| Object | 2017-09-18 |
—
|
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: 2017-09-18 | Statement: [Hurricane Maria, dateOfLandfall, 2017-09-18]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateOfLandfall Context triple: [Hurricane Maria, dateOfLandfall, 2017-09-18]
-
A.
firstLandfallBy
Indicates the location or entity where something (typically a storm, traveler, or object) initially makes landfall or first arrives from a journey over water or air.
-
B.
secondMajorLandfallDate
Indicates the calendar date on which an entity, such as a storm or similar event, makes its second significant landfall.
-
C.
firstLandfallYear
Indicates the calendar year in which something (typically a storm or similar event) first makes landfall.
-
D.
landfallLocation
Indicates the geographic location where a storm or similar weather system first makes landfall.
-
E.
reachedHurricaneStatusOn
Indicates the date or time at which a storm system intensified enough to be classified as a hurricane.
- 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_69c008cabc4081909723e2547c9d6cc0 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0639e64588190875e4e1e772fb336 |
completed | March 22, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69c05606fb50819082d1a5a91e5030b6 |
completed | March 22, 2026, 8:50 p.m. |
| PDg | Predicate description generation | batch_69c056c965ac8190b938502fa8c74e1b |
completed | March 22, 2026, 8:53 p.m. |
Created at: March 22, 2026, 4:25 p.m.