Triple
T585049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upstate New York (broad sense) |
E15138
|
entity |
| Predicate | terminology |
P5697
|
FINISHED |
| Object | usage and boundaries vary by context |
—
|
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: usage and boundaries vary by context | Statement: [Upstate New York (broad sense), terminology, usage and boundaries vary by context]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terminology Context triple: [Upstate New York (broad sense), terminology, usage and boundaries vary by context]
-
A.
terminologyNote
chosen
Indicates that there is an explanatory note or comment clarifying the use, meaning, or nuances of a specific term in the relationship.
-
B.
keyTerm
Indicates that a term functions as a primary or central concept within a given context or information structure.
-
C.
coinedTerm
Indicates that an entity originated and introduced a particular term or expression into use.
-
D.
notation
Indicates a conventional way of symbolically representing or writing something, such as concepts, quantities, or operations, within a specific system.
-
E.
lexicalChange
Indicates a relationship where one linguistic form is replaced, modified, or evolves into another form over time or across language varieties.
- 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_69a4935783b8819082b77726ec10cc42 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49b9874c88190bd1e08d4689ea124 |
completed | March 1, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69a494c9315c8190a773e8e00737d8a0 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.