Triple
T23565181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canadian border near Fortuna, North Dakota |
E579350
|
entity |
| Predicate | adjacentUSCounty |
P6346
|
FINISHED |
| Object |
Divide County
Divide County is a sparsely populated county in northwestern North Dakota known for its agricultural landscape and location along the Canadian border.
|
E1592564
|
NE FINISHED |
How this triple was built (3 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: Divide County | Statement: [Canadian border near Fortuna, North Dakota, adjacentUSCounty, Divide County]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Divide County Triple: [Canadian border near Fortuna, North Dakota, adjacentUSCounty, Divide County]
Generated description
Divide County is a sparsely populated county in northwestern North Dakota known for its agricultural landscape and location along the Canadian border.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentUSCounty Context triple: [Canadian border near Fortuna, North Dakota, adjacentUSCounty, Divide County]
-
A.
adjacentToCounty
chosen
Indicates that one county directly borders or touches another county geographically.
-
B.
hasNearbyCounty
Indicates that one county is geographically close to or directly adjacent to another county.
-
C.
adjacentCountySeat
Indicates that the county seat of one county is directly next to or bordering the county seat of another county.
-
D.
hasNearbyCountyBorder
Indicates that the borders of two counties are geographically close to each other, though not necessarily directly adjacent.
-
E.
isCornerCountyOf
Indicates that a county lies at or near the corner where two or more larger administrative regions (such as states or districts) meet.
- F. None of above.
Provenance (6 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_69e245fe24588190888f3aec8407d8e3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1af6c2930819090bc2b95725fbf18 |
completed | April 29, 2026, 7:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0f456377f081908cbc14309e111526 |
completed | May 21, 2026, 5:48 p.m. |
| NEDg | Description generation | batch_6a0f4650e36881909899a551725e6df4 |
completed | May 21, 2026, 5:52 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0f476e8eb88190a895453552c92b9a |
completed | May 21, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69f118bcc0b08190b25a8dddfd461a0e |
completed | April 28, 2026, 8:29 p.m. |
Created at: April 17, 2026, 6:34 p.m.