Triple
T15696947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umbwe Gate |
E380486
|
entity |
| Predicate | routeCharacterAccessed |
P120341
|
FINISHED |
| Object | steep |
—
|
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: steep | Statement: [Umbwe Gate, routeCharacterAccessed, steep]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: routeCharacterAccessed Context triple: [Umbwe Gate, routeCharacterAccessed, steep]
-
A.
routeCharacter
Indicates that a particular character is associated with, or serves as the defining focus of, a specific route or path within a structured sequence (such as in a story, game, or navigation system).
-
B.
routeAffected
Indicates that a transportation route is impacted or disrupted in some way, such as by delays, closures, or changes in service.
-
C.
routeTargeted
Indicates that a route is specifically directed toward or intended to reach a particular target entity or destination.
-
D.
routeUnder
Indicates that one route passes beneath another route or structure, typically at an underpass or similar crossing.
-
E.
routeMayInclude
Indicates that a given route can optionally pass through, contain, or involve a specified segment, location, or element as part of its path.
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0b4d6b5788190883746ee82c799f5 |
completed | April 16, 2026, 10:07 a.m. |
| PD | Predicate disambiguation | batch_69e0051d639481909a10614e8f83e659 |
completed | April 15, 2026, 9:37 p.m. |
| PDg | Predicate description generation | batch_69e0b4d01c9c81909f6b611e8144c838 |
completed | April 16, 2026, 10:07 a.m. |
Created at: April 10, 2026, 4:44 a.m.