Triple
T12386377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marathon Reservoir |
E295874
|
entity |
| Predicate | hasFishing |
P78242
|
FINISHED |
| Object | restricted fishing |
—
|
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: restricted fishing | Statement: [Marathon Reservoir, hasFishing, restricted fishing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFishing Context triple: [Marathon Reservoir, hasFishing, restricted fishing]
-
A.
hasFishingSpecies
Indicates that a location, body of water, or fishing area supports or contains one or more specific species that can be fished there.
-
B.
fishingActivity
Indicates an activity where an entity engages in catching or attempting to catch fish or other aquatic organisms.
-
C.
hasFishingSeason
chosen
Indicates that there is a defined time period during which fishing for a particular resource or in a particular area is permitted or regulated.
-
D.
fishingType
Indicates the specific method or style of fishing associated with an activity, event, or location.
-
E.
fishingUse
Indicates that one entity uses another as a tool, method, or context specifically for the activity of fishing.
- 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fbd489c819098233a111442762e |
completed | April 10, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69d93ed256788190b704cad171a4824e |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.