Triple
T4908406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Birmingham Zoo |
E109969
|
entity |
| Predicate | offersAttraction |
P59374
|
FINISHED |
| Object | carousel |
—
|
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: carousel | Statement: [Birmingham Zoo, offersAttraction, carousel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersAttraction Context triple: [Birmingham Zoo, offersAttraction, carousel]
-
A.
offersDayPlacesTo
Indicates that one entity provides or makes available daytime places or slots to another entity.
-
B.
offersDayPlaces
Indicates that an entity provides or makes available daytime places or slots (e.g., for care, activities, or services) to others.
-
C.
isAttractionFor
Indicates that one entity serves as an attraction or point of interest specifically intended for another entity (such as a person, group, or audience).
-
D.
servesAttraction
Indicates that one entity functions as or provides a service that supports or enhances the experience of a particular attraction.
-
E.
relatedAttraction
Indicates that one attraction is associated with or connected to another attraction in some relevant way.
- 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_69bd441180708190ba42ffb44fea533a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e765094819099481f4f2dd7c47d |
completed | March 20, 2026, 3:57 p.m. |
| PD | Predicate disambiguation | batch_69bd6c325e188190823836d79934e9bc |
completed | March 20, 2026, 3:48 p.m. |
| PDg | Predicate description generation | batch_69bd6cc228088190849f23b7bd4cf549 |
completed | March 20, 2026, 3:50 p.m. |
Created at: March 20, 2026, 1:29 p.m.