Triple
T26876033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Illinois lies generally northwest of Kentucky |
E676750
|
entity |
| Predicate | referenceState |
P169925
|
FINISHED |
| Object | Kentucky |
—
|
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: Kentucky | Statement: [Illinois lies generally northwest of Kentucky, referenceState, Kentucky]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: referenceState Context triple: [Illinois lies generally northwest of Kentucky, referenceState, Kentucky]
-
A.
refersToStateOf
Indicates that one entity denotes, describes, or is about the condition, status, or situation (state) of another entity.
-
B.
sourceState
Indicates the original or starting state from which a transition, change, or process begins.
-
C.
associatedState
Indicates that one entity is linked or connected to a particular state, condition, or status of another entity.
-
D.
regionReference
Indicates that one entity refers to, points to, or is associated with a specific region or area defined by another entity.
-
E.
referentRecord
Indicates that one record serves as a reference or pointer to another record within a data or information structure.
- F. None of above. chosen
Provenance (4 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_69eee9bb44988190b6e11652d028bc59 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f688d015908190ad5df37030ecf332 |
completed | May 2, 2026, 11:29 p.m. |
| PD | Predicate disambiguation | batch_69f68609c0b08190a8e1238a4d97c270 |
completed | May 2, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69f688034580819086a0f9100645f8ba |
completed | May 2, 2026, 11:25 p.m. |
Created at: April 27, 2026, 5:36 a.m.