Triple
T27907257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Michigan watershed |
E705817
|
entity |
| Predicate | hasPrimaryInflowType |
P4496
|
FINISHED |
| Object | surface runoff |
—
|
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: surface runoff | Statement: [Lake Michigan watershed, hasPrimaryInflowType, surface runoff]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryInflowType Context triple: [Lake Michigan watershed, hasPrimaryInflowType, surface runoff]
-
A.
hasPrimaryInflow
chosen
Indicates that one entity serves as the main source of inflowing material, energy, or influence into another entity.
-
B.
hasPrimaryTrafficType
Indicates that an entity is associated with a main or predominant type of traffic it handles or is designed for.
-
C.
hasPrimary
Indicates that one entity is designated as the main or most important instance (the primary) in relation to another entity.
-
D.
hasPrimarySourceType
Indicates that something is associated with a main or original type of source from which information or evidence is directly obtained.
-
E.
hasPrimaryAccessType
Indicates that an entity is associated with its main or default mode or category of access.
- 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_69ef96b5aad08190be36a277c31e7004 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fe7b1c506c8190869c1a22031e0571 |
completed | May 9, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69fe796b2bdc8190a86980d44008f875 |
completed | May 9, 2026, 12:01 a.m. |
Created at: April 27, 2026, 6:46 p.m.