Triple
T30916954
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | martial eagle |
E787605
|
entity |
| Predicate | topPredatorRole |
P22946
|
FINISHED |
| Object | apex aerial predator in African savannas |
—
|
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: apex aerial predator in African savannas | Statement: [martial eagle, topPredatorRole, apex aerial predator in African savannas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topPredatorRole Context triple: [martial eagle, topPredatorRole, apex aerial predator in African savannas]
-
A.
apexPredatorIn
chosen
Indicates that an entity is the top predator within a specified environment, ecosystem, or location, facing no regular natural predators there.
-
B.
predators
Indicates a relationship where one organism hunts, kills, and consumes another organism as a food source.
-
C.
mainPreySpecies
Indicates the species that serves as the primary prey or main food source for a given predator.
-
D.
roleInPredators
Indicates that an entity has a specific role or function within the context of predators or a predatory group.
-
E.
preysOn
Indicates that one entity hunts, kills, and consumes another entity as a food source.
- 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_69f224be300c8190a6513ce1ee0a7026 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f692b307488190a155de7798ec22fe |
completed | May 3, 2026, 12:11 a.m. |
| PD | Predicate disambiguation | batch_69f68b7ec098819080480998038de940 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 8:51 p.m.