Triple
T4562260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cape Flattery |
E121818
|
entity |
| Predicate | isExtremePointOf |
P47994
|
FINISHED |
| Object | contiguous United States |
—
|
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: contiguous United States | Statement: [Cape Flattery, isExtremePointOf, contiguous United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isExtremePointOf Context triple: [Cape Flattery, isExtremePointOf, contiguous United States]
-
A.
hasExtremePoint
chosen
Indicates that one entity possesses or includes another entity that is an extreme (e.g., maximum or minimum) point within its structure or boundary.
-
B.
isExtremalWhen
Indicates that a given entity or configuration attains an extreme value (such as a maximum or minimum) of some specified quantity or property under certain conditions.
-
C.
isReferencePointFor
Indicates that one entity serves as a positional or conceptual basis used to locate, measure, or interpret another entity.
-
D.
containsPoint
Indicates that a geometric region or shape includes a given point within its boundaries.
-
E.
isPointWhere
Indicates that one entity is the specific location or point at which another entity, event, or condition occurs or is defined.
- 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_69bd463f156881908a99aca69c5721ac |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd582f21648190b49284eb61b618c9 |
completed | March 20, 2026, 2:22 p.m. |
| PD | Predicate disambiguation | batch_69bd52254c648190a5144cfe8fa7e409 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:09 p.m.