Triple
T4963106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serengeti National Park |
E111455
|
entity |
| Predicate | migrationFeature |
P4575
|
FINISHED |
| Object | annual migration of about 1.5 million wildebeest |
—
|
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: annual migration of about 1.5 million wildebeest | Statement: [Serengeti National Park, migrationFeature, annual migration of about 1.5 million wildebeest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: migrationFeature Context triple: [Serengeti National Park, migrationFeature, annual migration of about 1.5 million wildebeest]
-
A.
migrationFrom
Indicates that an entity has moved, originated, or been transferred away from a specified source location or context.
-
B.
migration
Indicates the movement of entities from one location or context to another, often across boundaries or over time.
-
C.
migrationPolicy
Indicates the rules or strategies governing how entities move, transfer, or transition from one context, location, or state to another.
-
D.
migrationEvent
Indicates an event in which one or more entities move or relocate from one place or context to another, typically across defined boundaries or regions.
-
E.
migrationPattern
chosen
Indicates the typical routes, timing, and destinations followed by entities as they move periodically from one location or region to another.
- 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_69bd4419393c819086319a6fe4bf8542 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd72e49b048190bac55d9e7a6f7963 |
completed | March 20, 2026, 4:16 p.m. |
| PD | Predicate disambiguation | batch_69bd71447fe88190bb62c5e8753da7a7 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:32 p.m.