Triple
T982594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mason–Dixon Line |
E21202
|
entity |
| Predicate | followsParallel |
P21926
|
FINISHED |
| Object | 39th parallel north (approximate) |
—
|
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: 39th parallel north (approximate) | Statement: [Mason–Dixon Line, followsParallel, 39th parallel north (approximate)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsParallel Context triple: [Mason–Dixon Line, followsParallel, 39th parallel north (approximate)]
-
A.
follows
Indicates that one entity comes after, moves behind, or acts in accordance with another entity in time, space, or sequence.
-
B.
followsFrom
Indicates that one fact, event, or state logically or causally results from, is implied by, or comes as a consequence of another.
-
C.
followsCycle
Indicates that one entity adheres to or repeats a recurring sequence, pattern, or cycle defined or exemplified by another entity.
-
D.
followsWork
Indicates that one work (such as a publication, version, or creative piece) comes directly after another in sequence or succession.
-
E.
structureParallels
Indicates that the structural organization or arrangement of one entity closely corresponds to or mirrors that of another.
- 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_69a493c383dc8190a03257f22d4b4183 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b49284ac8190b1d7c828d728893c |
completed | March 1, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69a4b2aa219081908a6b0ef786b4aa52 |
completed | March 1, 2026, 9:42 p.m. |
| PDg | Predicate description generation | batch_69a4b345f890819092b51bf8128da461 |
completed | March 1, 2026, 9:44 p.m. |
Created at: March 1, 2026, 7:41 p.m.