Triple
T11061700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Typhoon Haiyan |
E261522
|
entity |
| Predicate | maximumSustainedWinds_1min |
P40034
|
FINISHED |
| Object | 170 knots |
—
|
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: 170 knots | Statement: [Typhoon Haiyan, maximumSustainedWinds_1min, 170 knots]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maximumSustainedWinds_1min Context triple: [Typhoon Haiyan, maximumSustainedWinds_1min, 170 knots]
-
A.
maximumSustainedWinds
chosen
Indicates the highest wind speed that is maintained continuously over a specified averaging period, rather than in brief gusts.
-
B.
maximumGusts
Indicates the relationship where a recorded wind gust value represents the highest (maximum) gust observed within a specified time or context.
-
C.
windSpeed
Indicates the measured or estimated rate at which wind is moving at a given location and time.
-
D.
dateOf100mphRecord
Indicates the date on which an entity achieved a 100 mph performance record.
-
E.
windDirectionAtLandfall
Indicates the direction from which the wind is blowing at the moment and location where a storm makes landfall.
- 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_69d6aa98650481908609c7c56bfa7902 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798ea834c819099401e69f995c59f |
completed | April 9, 2026, 12:17 p.m. |
| PD | Predicate disambiguation | batch_69d74411d9e881908c0eeafa0f38e4b6 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.