Triple
T35980274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LaSalle |
E1040542
|
entity |
| Predicate | borderingStateAcrossWater |
P201022
|
FINISHED |
| Object | Michigan |
—
|
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: Michigan | Statement: [LaSalle, borderingStateAcrossWater, Michigan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderingStateAcrossWater Context triple: [LaSalle, borderingStateAcrossWater, Michigan]
-
A.
borderingCountryAcrossWater
Indicates that one country is geographically separated from another by a body of water yet lies close enough to be considered a neighboring country across that water.
-
B.
borderingWaters
Indicates that a geographic area directly touches or is adjacent to a particular body of water.
-
C.
bordersStateAcrossSea
Indicates that one state is separated from another by a sea but still directly borders it across that body of water.
-
D.
borderStateOf
Indicates that one state shares a common boundary or border with another state.
-
E.
crossingRegime
Indicates the regulatory or procedural framework under which a boundary or checkpoint is crossed.
- 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_69f76e28293c8190ae3f4e2208b87117 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ffc1550cb481908628e446d9b67f7b |
completed | May 9, 2026, 11:20 p.m. |
| PD | Predicate disambiguation | batch_69ffc10a74708190ae90e2c378791f70 |
completed | May 9, 2026, 11:19 p.m. |
| PDg | Predicate description generation | batch_69ffc15434c8819093aa3b33813613be |
completed | May 9, 2026, 11:20 p.m. |
Created at: May 3, 2026, 4:07 p.m.