Triple
T30031128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bohu County |
E763019
|
entity |
| Predicate | hasNotableBodyOfWater |
P106673
|
FINISHED |
| Object | Bosten Lake |
—
|
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: Bosten Lake | Statement: [Bohu County, hasNotableBodyOfWater, Bosten Lake]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableBodyOfWater Context triple: [Bohu County, hasNotableBodyOfWater, Bosten Lake]
-
A.
hasBodyOfWaterType
Indicates that a body of water is classified as being of a particular type or category (such as lake, river, ocean, etc.).
-
B.
hasWatersOf
chosen
Indicates that a geographic or physical entity contains, is traversed by, or is otherwise characterized by specific bodies or types of water.
-
C.
locatedInBodyOfWater
Indicates that an entity is situated within or on the surface of a specific body of water.
-
D.
adjacentToBodyOfWater
Indicates that one entity is directly next to or bordering a body of water, such as a lake, river, or ocean.
-
E.
hasNoCoastline
Indicates that the referenced place is landlocked and does not border any sea or ocean.
- 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_69f2246fb2b88190acff36bf7975c8f0 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a000fda03948190881b7275f249768f |
completed | May 10, 2026, 4:55 a.m. |
| PD | Predicate disambiguation | batch_6a000f607f1881908ee750d58da91690 |
completed | May 10, 2026, 4:53 a.m. |
Created at: April 29, 2026, 6:50 p.m.