Triple
T3678638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Discovery Island |
E78055
|
entity |
| Predicate | animalExhibitsInclude |
P22362
|
FINISHED |
| Object | lemurs |
—
|
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: lemurs | Statement: [Discovery Island, animalExhibitsInclude, lemurs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: animalExhibitsInclude Context triple: [Discovery Island, animalExhibitsInclude, lemurs]
-
A.
hasExhibitSpecies
chosen
Indicates that an exhibit or display includes or features a particular species.
-
B.
zooSection
Indicates that one entity is a specific section or area within a zoo where the other entity is located, organized, or assigned.
-
C.
zooSpecialization
Indicates that one entity is a zoo whose primary focus or expertise is specialized in the type, category, or group represented by the other entity.
-
D.
Reptile HouseStatus
Indicates the operational or condition status of a reptile house facility in relation to its use or availability.
-
E.
zooType
Indicates the classification or category of a zoo, such as its type or kind.
- 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_69ad85e18c1c8190be8aafb227f39f48 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc46599188190a046eddb0d85c483 |
completed | March 8, 2026, 6:48 p.m. |
| PD | Predicate disambiguation | batch_69adb84be1fc81909721c871babb4633 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:25 p.m.