Triple
T36244763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Shinji |
E891627
|
entity |
| Predicate | supportsFisheryFor |
P137299
|
FINISHED |
| Object | shijimi clams |
—
|
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: shijimi clams | Statement: [Lake Shinji, supportsFisheryFor, shijimi clams]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsFisheryFor Context triple: [Lake Shinji, supportsFisheryFor, shijimi clams]
-
A.
supportsFishery
chosen
Indicates that one entity provides resources, conditions, or actions that maintain or enhance the viability of a fishery.
-
B.
containsFishery
Indicates that one entity includes, encompasses, or has within its area a fishery or fishing-related operation.
-
C.
managedForFisheriesBy
Indicates that the management or oversight of fisheries-related activities or resources is carried out by a specified agent or authority.
-
D.
fisheryType
Indicates the specific category or kind of fishery associated with an entity, such as its operational or regulatory classification.
-
E.
hasShoreFishing
Indicates that a location or body of water provides opportunities or facilities for fishing from the shore.
- 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_69f76e44993481908fa75e4c48d0aab3 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:09 p.m.