Triple
T402054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biscayne National Park |
E9305
|
entity |
| Predicate | activities |
P8834
|
FINISHED |
| Object | snorkeling |
—
|
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: snorkeling | Statement: [Biscayne National Park, activities, snorkeling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: activities Context triple: [Biscayne National Park, activities, snorkeling]
-
A.
activity
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
-
B.
activityType
chosen
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
-
C.
typicalActivity
Indicates that an entity is commonly or characteristically engaged in a particular activity.
-
D.
activityTime
Indicates the time period during which an activity occurs or is scheduled to take place.
-
E.
event
Indicates that there exists an occurrence or happening involving one or more entities, typically situated in time and possibly space.
- 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_69a2e8004cb88190b92ed1add6abf41a |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ec9f77888190bcc2bc68d201ed35 |
completed | Feb. 28, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69a2e96ee4ec8190a5c0e3f491d3963d |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.