Triple
T993145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Diego Zoo Safari Park |
E21434
|
entity |
| Predicate | hasVisitorServices |
P22278
|
FINISHED |
| Object | restaurants and food concessions |
—
|
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: restaurants and food concessions | Statement: [San Diego Zoo Safari Park, hasVisitorServices, restaurants and food concessions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVisitorServices Context triple: [San Diego Zoo Safari Park, hasVisitorServices, restaurants and food concessions]
-
A.
hasTypeOfVisitorExperience
Indicates that an entity is associated with a particular category or kind of visitor experience it provides or involves.
-
B.
hasVisitorType
Indicates the type or category of visitor associated with an entity (e.g., guest, customer, tourist, patient).
-
C.
hasServiceTo
Indicates that one entity provides, offers, or operates a service for or directed toward another entity.
-
D.
hasVisitorPolicy
Indicates that an entity has an established policy governing the presence, behavior, or permissions of visitors.
-
E.
isServedAt
Indicates that something (such as food, drink, or a service) is provided or made available at a particular place or venue.
- F. None of above. chosen
Provenance (4 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_69a493c476b48190b41fc5e793171cc6 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4c3f7b48190a31308bdc09817c6 |
completed | March 1, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69a4b2adbde48190b07966d0c3179516 |
completed | March 1, 2026, 9:42 p.m. |
| PDg | Predicate description generation | batch_69a4b38723d8819098b861cba5cad4ee |
completed | March 1, 2026, 9:45 p.m. |
Created at: March 1, 2026, 7:41 p.m.