Triple
T7585248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sea Cliffs exhibit |
E179593
|
entity |
| Predicate | featuresAnimalClass |
P77243
|
FINISHED |
| Object | marine mammal |
—
|
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: marine mammal | Statement: [Sea Cliffs exhibit, featuresAnimalClass, marine mammal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresAnimalClass Context triple: [Sea Cliffs exhibit, featuresAnimalClass, marine mammal]
-
A.
animalClassFeatured
chosen
Indicates that a particular animal class is highlighted or prominently presented in relation to something (such as content, a display, or a context).
-
B.
animalTypeFeatured
Indicates that a particular type or category of animal is highlighted or prominently showcased in a given context.
-
C.
featuresTalkingAnimals
Indicates that the subject includes or depicts animals that can speak or communicate using human language.
-
D.
featuresSpecies
Indicates that something includes, presents, or highlights a particular species as part of its content or composition.
-
E.
animalForm
Indicates that one entity takes the shape, body, or characteristics of an animal.
- 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_69c69f335248819093c1006f30513708 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f995c8a8819089817bd679640017 |
completed | March 27, 2026, 9:41 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e04c2c8190a889d928515d9b8e |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:52 p.m.