Triple
T26721754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Weeki Wachee, Florida |
E673720
|
entity |
| Predicate | mermaidShowVenue |
P112843
|
FINISHED |
| Object | Weeki Wachee Springs State Park |
—
|
NE NERFINISHED |
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: Weeki Wachee Springs State Park | Statement: [Weeki Wachee, Florida, mermaidShowVenue, Weeki Wachee Springs State Park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mermaidShowVenue Context triple: [Weeki Wachee, Florida, mermaidShowVenue, Weeki Wachee Springs State Park]
-
A.
hasVenueFor
chosen
Indicates that one entity provides or serves as the location or setting where an event, activity, or function takes place for another entity.
-
B.
intendedPerformanceVenue
Indicates the venue or location where a performance is planned or intended to take place.
-
C.
hasVenueIn
Indicates that an event, activity, or occurrence takes place at a specific venue located within a particular geographic area or location.
-
D.
presentsAt
Indicates that one entity delivers or gives a presentation, talk, or performance at a particular event, venue, or occasion.
-
E.
homeVenueAppearances
Indicates the number of times an entity has appeared or performed at its designated home venue.
- 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_69eecda481d08190aea69f2f7c745f56 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f61802c8f081908fe3a2e7c3b4317b |
completed | May 2, 2026, 3:28 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 3:41 a.m.