Triple
T27753125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serengeti wildebeest migration |
E701262
|
entity |
| Predicate | peakCalvingSeason |
P108895
|
FINISHED |
| Object | January to March |
—
|
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: January to March | Statement: [Serengeti wildebeest migration, peakCalvingSeason, January to March]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: peakCalvingSeason Context triple: [Serengeti wildebeest migration, peakCalvingSeason, January to March]
-
A.
peakSeasonMonth
chosen
Indicates the month or months during which something (such as demand, activity, or occurrence) reaches its highest or most intense level.
-
B.
typicalSeasonNorthernHemisphereStart
Indicates the season in the Northern Hemisphere that typically begins at the given time or date.
-
C.
culminationSeason
Indicates the season of the year in which an event, process, or activity reaches its peak or final stage.
-
D.
coldestSeason
Indicates the season during which a place or region experiences its lowest typical temperatures compared to other seasons.
-
E.
occursInSeasonInNorthernHemisphere
Indicates that an event or phenomenon takes place during a specified season as defined for the Northern Hemisphere.
- 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_69ef6a5193808190816eb7d0020b2d87 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f63894e5848190aec428392562ab06 |
completed | May 2, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_69f6370c8c7c8190a02ea82847bb6e76 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 4:21 p.m.